© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14773
    Prev
    Next
    INDEX
    Explanations

    references to actions, treatments, and phenomena related to medical or technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or scientific language related to process details, measurements, and research methods.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    descriptions of conditions or processes where something is exposed to temperature changes or heat treatment.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    numerical values and measurements (temperatures, quantities, durations, and other specific numeric data).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.60
     CreateTagHelper
    -0.46
    ConstraintMaker
    -0.45
    VYMaps
    -0.43
     StatelessWidget
    -0.42
     StatefulWidget
    -0.42
    hasMoreElements
    -0.41
    subtle
    -0.40
    webElementXpaths
    -0.39
    fluffy
    -0.38
    POSITIVE LOGITS
     لمدة
    1.77
     lasted
    1.16
     selama
    1.09
     протягом
    1.09
     gedurende
    1.06
     течение
    1.00
     lasting
    0.96
     briefly
    0.93
     протяжении
    0.93
     lasts
    0.91
    Activations Density 1.230%

    No Known Activations