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. 653
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure, particularly those that involve defining variable attributes and layout in a coded context

    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
    aufbau
    -0.36
    glTexCoord
    -0.34
    zzleHttp
    -0.33
    lomer
    -0.33
    ari
    -0.33
    lay
    -0.33
    ente
    -0.33
    glColor
    -0.32
    CrossRef
    -0.32
    BorderLayout
    -0.32
    POSITIVE LOGITS
     الحره
    0.74
     otomatig
    0.63
    identical
    0.63
    GEBURTSDATUM
    0.62
    SharedDtor
    0.59
    IntoConstraints
    0.58
     ciascuno
    0.53
     repeti
    0.53
     identical
    0.52
    Personensuche
    0.52
    Activations Density 1.015%

    No Known Activations