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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 140
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations and funding sources

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

    academic or scientific citation details and references.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Monfieur
    -0.96
     myſelf
    -0.91
    majánló
    -0.87
     pleaſure
    -0.86
     ſch
    -0.86
     Eſ
    -0.81
     auffi
    -0.81
     unſ
    -0.81
     ſche
    -0.80
     ſta
    -0.80
    POSITIVE LOGITS
    idorm
    0.34
    <strong>
    0.31
     l
    0.29
    MADRID
    0.28
    EU
    0.28
    Spain
    0.27
     Bis
    0.27
    Bis
    0.27
     EU
    0.27
    <blockquote>
    0.25
    Activations Density 0.267%

    No Known Activations