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. 12-GEMMASCOPE-RES-16K
    6. 6183
    Prev
    Next
    INDEX
    Explanations

    specific mathematical or statistical expressions and numeric data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funniest
    -0.38
     cutest
    -0.37
     bug
    -0.36
     HELLO
    -0.36
    ái
    -0.36
     gră
    -0.35
    FLUSH
    -0.35
     ModelExpression
    -0.35
     Pate
    -0.35
     overboard
    -0.34
    POSITIVE LOGITS
     AssemblyTitle
    0.98
    دانشنامهٔ
    0.90
    EndGlobalSection
    0.88
    ValueStyle
    0.86
    MigrationBuilder
    0.86
    argout
    0.80
    esez
    0.79
    ChildScrollView
    0.78
    __((
    0.77
    الحياه
    0.77
    Activations Density 0.472%

    No Known Activations