© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8433
    Prev
    Next
    INDEX
    Explanations

    names of high-profile individuals and titles associated with political and entertainment contexts

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

    First names of notable people

    np_acts-logits-general · gemini-2.0-flash

    famous names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.88
     a
    -0.75
     in
    -0.73
     the
    -0.72
     at
    -0.72
    .
    -0.71
     
    -0.69
    /
    -0.67
    :
    -0.66
     and
    -0.64
    POSITIVE LOGITS
    CloseOperation
    0.99
     Houſe
    0.98
     houſe
    0.93
    RenderAtEndOf
    0.88
     Roskov
    0.87
     ſever
    0.87
     فريبيس
    0.86
     Monfieur
    0.80
     iſt
    0.78
     Perſ
    0.77
    Activations Density 1.003%

    No Known Activations