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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12559
    Prev
    Next
    INDEX
    Explanations

    issues related to public policy and legislative actions

    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
     jährlich
    -0.51
    年間
    -0.50
     anuales
    -0.49
    めます
    -0.48
    jaro
    -0.45
    年には
    -0.45
    hosa
    -0.44
     jähr
    -0.42
     ̄)
    -0.42
    ネート
    -0.41
    POSITIVE LOGITS
     yesterday
    3.44
    yesterday
    2.90
     today
    2.88
     Yesterday
    2.81
    Yesterday
    2.74
     tonight
    2.72
     Tuesday
    2.63
     Thursday
    2.62
     Wednesday
    2.58
     Monday
    2.56
    Activations Density 1.083%

    No Known Activations