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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43356
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to coding frameworks and data structures

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    migrationBuilder
    -0.99
    HostException
    -0.97
    openzeppelin
    -0.91
    ()]);
    -0.90
    uxxxx
    -0.89
    IsMutable
    -0.89
    MigrationBuilder
    -0.88
    Personensuche
    -0.88
    URLException
    -0.86
    setupUi
    -0.84
    POSITIVE LOGITS
    Section
    0.47
     Section
    0.47
    Region
    0.45
    End
    0.45
    end
    0.45
    形
    0.45
    的是
    0.44
    Result
    0.43
    Month
    0.43
    형
    0.43
    Activations Density 0.238%

    No Known Activations