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. 2053
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to programming frameworks and data structures

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

    technical filesystem paths and source-code artifact identifiers, such as directories, package/module names, file extensions, and build-related filenames.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    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
     CreateTagHelper
    -0.73
    AndEndTag
    -0.62
    afficheront
    -0.61
     Administrativna
    -0.56
    reportWebVitals
    -0.55
     ProtoMessage
    -0.54
    +:+
    -0.54
     resourceCulture
    -0.53
    ientras
    -0.51
    Tikang
    -0.51
    POSITIVE LOGITS
    </em>
    0.47
    </strong>
    0.44
    ScopeManager
    0.41
    </u>
    0.40
     trava
    0.37
    向
    0.36
    PropTypes
    0.36
    </b>
    0.36
     wim
    0.35
     West
    0.35
    Activations Density 1.067%

    No Known Activations