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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4192
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting symbols in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="#">
    -0.58
     hinaus
    -0.54
    ніципалі
    -0.52
    willReturn
    -0.52
     dono
    -0.52
    횟
    -0.52
     nonUne
    -0.50
     No
    -0.50
    ītā
    -0.49
    UnusedPrivate
    -0.49
    POSITIVE LOGITS
    CloseOperation
    0.84
     WebDriverWait
    0.79
    AnimationsModule
    0.75
    󠁢
    0.74
     ***!
    0.72
    PreAuthorize
    0.68
    niająca
    0.68
    ScopeManager
    0.68
    migrationBuilder
    0.65
    irical
    0.64
    Activations Density 0.050%

    No Known Activations