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 - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8623
    Prev
    Next
    INDEX
    Explanations

    content related to scientific publications and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.99
     Baillargeon
    -0.87
    MigrationBuilder
    -0.82
    RegressionTest
    -0.77
    Diweddarwch
    -0.73
    MessageOf
    -0.68
     متعلقه
    -0.64
    BeginContext
    -0.62
     ISNI
    -0.60
     airbag
    -0.60
    POSITIVE LOGITS
    setContentView
    0.56
    IntoConstraints
    0.52
     समीक्षाओं
    0.48
    ########.
    0.46
    getDescriptor
    0.46
    closures
    0.46
    Datuak
    0.45
    frastructure
    0.44
     zal
    0.44
    ponses
    0.43
    Activations Density 6.891%

    No Known Activations