© 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. 14354
    Prev
    Next
    INDEX
    Explanations

    words relating to generalized quantity or frequency

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

    the word "any" used to indicate non-specific quantities or possibilities.

    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
     Various
    -0.36
    PostBack
    -0.36
    XmlAccessorType
    -0.35
    nutí
    -0.33
    Various
    -0.33
     illetve
    -0.31
    ss
    -0.31
    both
    -0.30
    without
    -0.30
    geschoss
    -0.30
    POSITIVE LOGITS
    ftagPool
    0.84
     المعيارى
    0.84
    OGND
    0.81
     CreateTagHelper
    0.75
    GEBURTSDATUM
    0.75
    脚注の使い方
    0.73
    DockStyle
    0.73
     springfox
    0.71
     kasarigan
    0.69
     nakalista
    0.69
    Activations Density 0.763%

    No Known Activations