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. 21-GEMMASCOPE-RES-16K
    6. 6410
    Prev
    Next
    INDEX
    Explanations

    references to magazines and their publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PATH
    -0.40
    征詢我
    -0.38
    ratos
    -0.37
    WebElementEntity
    -0.37
     Github
    -0.37
     GoFundMe
    -0.36
    Thierry
    -0.36
    ruptedException
    -0.36
     Pathol
    -0.36
     manifest
    -0.35
    POSITIVE LOGITS
     magazine
    1.08
    magazine
    0.96
     magazines
    0.94
     Magazine
    0.92
    Magazine
    0.88
     MAGAZINE
    0.87
    MAGAZINE
    0.76
    杂志
    0.71
    magaz
    0.69
     Magazin
    0.69
    Activations Density 0.194%

    No Known Activations