© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8691
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts and processes

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

    phrases that list multiple items or alternatives separated by "and" or "or" conjunctions.

    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
    RTSC
    -0.38
    それでは
    -0.31
     впер
    -0.31
    以外は
    -0.31
    FunctionFlags
    -0.31
    SequentialGroup
    -0.31
    以降
    -0.31
     rest
    -0.31
    likle
    -0.30
    はじめに
    -0.30
    POSITIVE LOGITS
     another
    4.16
    another
    3.66
    Another
    3.44
     Another
    3.38
     ANOTHER
    2.84
     otro
    2.83
     otra
    2.73
    另一个
    2.69
    另一個
    2.63
    另一
    2.52
    Activations Density 1.773%

    No Known Activations