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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11316
    Prev
    Next
    INDEX
    Explanations

    technical terms and function definitions in programming-related texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -1.02
    RegressionTest
    -0.88
    PreferredItem
    -0.88
    </tfoot>
    -0.85
    AsUp
    -0.82
    migrationBuilder
    -0.82
     nahilalakip
    -0.82
    SequentialGroup
    -0.81
    enterOuterAlt
    -0.80
    DoubleQuotes
    -0.78
    POSITIVE LOGITS
     go
    0.45
     panic
    0.43
    go
    0.42
    cher
    0.40
    Package
    0.40
     drop
    0.40
    gon
    0.40
     Drop
    0.39
     Go
    0.39
    Go
    0.39
    Activations Density 0.405%

    No Known Activations