Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7889
    Prev
    Next
    INDEX
    Explanations

    elements related to data formatting and database structure

    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
    requireNonNull
    -0.39
     Antigen
    -0.34
    marvel
    -0.34
     band
    -0.34
    Footnote
    -0.32
    NRAS
    -0.32
     zout
    -0.31
    AndroidJUnit
    -0.30
     Heist
    -0.30
    QString
    -0.30
    POSITIVE LOGITS
    msgTypes
    0.57
    ніципалі
    0.54
    RegressionTest
    0.54
    AndEndTag
    0.53
    verwijspagina
    0.51
    HtmlAttribute
    0.50
     GenerationType
    0.50
    rawDesc
    0.49
     '\\;'
    0.49
    +#+#
    0.49
    Activations Density 0.501%

    No Known Activations