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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9707
    Prev
    Next
    INDEX
    Explanations

    elements related to functions and arrays in programming code

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

    whitespace and indentation tokens in source code.

    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
     ExecuteAsync
    -0.60
     محفوظة
    -0.57
     Normdatei
    -0.57
     AssemblyVersion
    -0.54
    OGND
    -0.48
    jsxFileName
    -0.47
    endpush
    -0.45
    IsContent
    -0.45
     يتيمه
    -0.44
     BoxFit
    -0.44
    POSITIVE LOGITS
     $
    1.03
    $
    0.90
    ($
    0.56
     ($
    0.56
     $_
    0.53
    $_
    0.53
    @$
    0.53
    foreach
    0.52
     @$
    0.51
    array
    0.50
    Activations Density 0.185%

    No Known Activations