© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9921
    Prev
    Next
    INDEX
    Explanations

    terms related to previews and outcomes in a document context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.89
    AccessorTable
    -0.88
    awtextra
    -0.71
    LookAnd
    -0.70
    MigrationBuilder
    -0.69
     defaultstate
    -0.67
    ResumeLayout
    -0.63
     Caine
    -0.61
    RegistryLite
    -0.59
     resourceCulture
    -0.58
    POSITIVE LOGITS
     Futures
    0.72
     preview
    0.71
    Future
    0.71
    Preview
    0.68
     Future
    0.68
    Futures
    0.66
     Preview
    0.65
     futures
    0.64
     PREVIEW
    0.63
     Pathways
    0.61
    Activations Density 0.171%

    No Known Activations