Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2545
    Prev
    Next
    INDEX
    Explanations

    HTML list element structures

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

    HTML list items

    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
     للمعارف
    -0.93
     мәкал
    -0.91
     незавершена
    -0.87
     tartalomajánló
    -0.81
    TagMode
    -0.79
     $_(
    -0.78
     queſta
    -0.77
     transfieras
    -0.77
     autorytatywna
    -0.75
     indígen
    -0.73
    POSITIVE LOGITS
    :
    0.43
    ,
    0.43
    сток
    0.42
     used
    0.40
     fark
    0.39
     deles
    0.38
    ;
    0.38
     (
    0.37
    .
    0.36
    '
    0.36
    Activations Density 0.014%

    No Known Activations