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. 24-GEMMASCOPE-RES-16K
    6. 2229
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and events in sports history

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

    "...Hall of Fame"

    np_acts-logits-general · gemini-2.0-flash

    Hall of Fame induction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.62
    ValueStyle
    -0.57
    MethodManager
    -0.57
    IntoConstraints
    -0.54
    aarrggbb
    -0.54
    SharedDtor
    -0.53
     onPostExecute
    -0.52
    Erreferentziak
    -0.51
     GeoNames
    -0.51
     beginnetje
    -0.50
    POSITIVE LOGITS
     induction
    1.26
     inducted
    1.23
     Hall
    1.21
     induc
    1.20
     Induction
    1.09
     induct
    1.06
    Induction
    1.04
     indu
    1.02
    Indu
    1.01
     hall
    1.01
    Activations Density 0.165%

    No Known Activations