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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5054
    Prev
    Next
    INDEX
    Explanations

    references to political movements and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Chriſt
    -0.67
     Majefty
    -0.64
     caufe
    -0.64
    ientôt
    -0.60
     cauſe
    -0.59
     anteriormente
    -0.58
    SqlSession
    -0.58
     Jefus
    -0.58
     himſelf
    -0.56
     Chrift
    -0.56
    POSITIVE LOGITS
     مشين
    0.87
     Grams
    0.63
     (...
    0.58
     RECIPE
    0.56
     profoundly
    0.55
    invokeLater
    0.53
     («
    0.53
     inexorable
    0.52
    ?«
    0.52
     (…)
    0.51
    Activations Density 0.048%

    No Known Activations