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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8013
    Prev
    Next
    INDEX
    Explanations

    references to reported events or actions in news articles

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

    Followed by parenthetical source or reference

    np_acts-logits-general · gemini-2.0-flash

    according to or bladder structural

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     netto
    -0.50
     szóci
    -0.50
     email
    -0.47
    |_
    -0.47
     Bring
    -0.44
    額
    -0.44
    deln
    -0.44
    Interess
    -0.44
     ple
    -0.43
    __);
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.91
     ModelExpression
    0.79
     AFP
    0.79
    aarrggbb
    0.79
     Vainqueur
    0.73
    oredCriteria
    0.72
    AFP
    0.69
     varandra
    0.68
     afp
    0.67
    ніципа
    0.67
    Activations Density 0.054%

    No Known Activations