© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 83327
    Prev
    Next
    INDEX
    Explanations

    occurrences of closing parentheses in the text

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

    closing parentheses or bracket following code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.03
     betweenstory
    -1.01
    AddTagHelper
    -0.86
     ſon
    -0.79
     juſ
    -0.77
     itſelf
    -0.73
    wiſe
    -0.72
    ſelves
    -0.71
    AutoScaleMode
    -0.70
     ſtate
    -0.70
    POSITIVE LOGITS
    ']->
    0.69
    ()->
    0.68
    ().
    0.62
    ]->
    0.59
    ())->
    0.56
    ->
    0.54
    >().
    0.54
    (&:
    0.52
    _->
    0.51
    ()).
    0.51
    Activations Density 0.011%

    No Known Activations