© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6935
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs or expressions related to setting values or configurations

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

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    weil
    -0.43
    titleMargin
    -0.39
     UIImageView
    -0.39
    ционное
    -0.37
    bobox
    -0.36
    QLabel
    -0.36
    wakili
    -0.36
    RUnlock
    -0.36
     QLabel
    -0.36
     resourceCulture
    -0.35
    POSITIVE LOGITS
     GenerationType
    1.05
    GenerationType
    0.69
    دانشنامهٔ
    0.58
     Normdatei
    0.56
    zzleHttp
    0.55
     للمعارف
    0.54
    ValueGeneration
    0.53
     تضيفلها
    0.52
     mécan
    0.51
    AutoField
    0.49
    Activations Density 0.001%

    No Known Activations