© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    elements related to data handling and manipulation in programming contexts

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

    function parameters and arguments in code, particularly those with assigned values using equals signs.

    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
    AccessorTable
    -0.53
     nakalista
    -0.52
     BorderSide
    -0.46
     scattata
    -0.45
     الحره
    -0.45
    parsedMessage
    -0.45
     ErrIntOverflow
    -0.44
     dAtA
    -0.44
    RTSC
    -0.44
    BoxLayout
    -0.42
    POSITIVE LOGITS
    =
    0.69
    =$
    0.54
    ValueStyle
    0.52
    =[
    0.52
    =
    0.50
     =
    0.49
    ={
    0.45
    =(
    0.44
    chemise
    0.43
    _=
    0.42
    Activations Density 0.431%

    No Known Activations