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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12261
    Prev
    Next
    INDEX
    Explanations

    references to web-related structures and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.80
    RTSC
    -0.68
     متعلقه
    -0.65
    MigrationBuilder
    -0.64
    interopRequire
    -0.64
    providedIn
    -0.62
     estekak
    -0.62
    LookAnd
    -0.61
    RenderAtEndOf
    -0.61
    ยว
    -0.61
    POSITIVE LOGITS
     site
    4.29
    site
    3.57
     Site
    3.55
    Site
    3.43
     sites
    3.16
     SITE
    3.11
    SITE
    2.85
     Sites
    2.70
    sites
    2.48
    Sites
    2.41
    Activations Density 0.376%

    No Known Activations