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. 11-GEMMASCOPE-RES-16K
    6. 6084
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols, likely focusing on angle brackets or other punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ren
    -0.60
    en
    -0.56
    PHY
    -0.51
    Пу
    -0.49
    eden
    -0.49
     Mitter
    -0.49
    ')}}
    -0.49
    Hend
    -0.49
    es
    -0.48
    Benson
    -0.48
    POSITIVE LOGITS
    enumi
    1.21
     cref
    1.06
     AssemblyCulture
    1.05
     numberWith
    1.03
    原始内容存档于
    1.02
    principalColumn
    1.00
    Revenir
    0.99
     MainAxisSize
    0.97
    FOOTNOTES
    0.95
     snippetHide
    0.94
    Activations Density 0.046%

    No Known Activations