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. 7429
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to matrices and their properties

    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
     AssemblyCompany
    -0.46
    WithIOException
    -0.43
    principalColumn
    -0.42
     Landwir
    -0.40
     plan
    -0.38
     nôtre
    -0.38
     Favor
    -0.38
     program
    -0.38
    FunctionFlags
    -0.37
     favor
    -0.37
    POSITIVE LOGITS
    setVerticalGroup
    0.57
    libft
    0.56
     ABS
    0.56
    $|
    0.55
     CWE
    0.54
    awtextra
    0.53
    abs
    0.49
    UrlResolution
    0.48
    CloseOperation
    0.48
    LLocation
    0.47
    Activations Density 0.876%

    No Known Activations