© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10981
    Prev
    Next
    INDEX
    Explanations

    names of places and geographic identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.59
     a
    -0.58
     
    -0.58
    <eos>
    -0.57
     (
    -0.55
     online
    -0.54
     Global
    -0.53
     put
    -0.53
    :
    -0.53
     dis
    -0.52
    POSITIVE LOGITS
     ་་
    0.84
     Efq
    0.77
    Autoritní
    0.74
     Majefty
    0.71
     Roskov
    0.70
     Eccle
    0.70
    ſelf
    0.69
     للمعارف
    0.69
    setVerticalGroup
    0.69
     FontFamily
    0.69
    Activations Density 0.125%

    No Known Activations