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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4402
    Prev
    Next
    INDEX
    Explanations

    references to cleaning and the presence of blood or stains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uncin
    -0.50
     Janvier
    -0.45
     paren
    -0.45
     Urlaub
    -0.45
     bral
    -0.44
     demar
    -0.43
     ✭✭
    -0.42
    otene
    -0.42
     campan
    -0.42
     crippling
    -0.42
    POSITIVE LOGITS
    ContentAlignment
    0.68
     Waray
    0.67
     wiping
    0.66
    MethodManager
    0.66
    Rinse
    0.66
    MigrationBuilder
    0.64
    empio
    0.64
     Path
    0.63
     Rinse
    0.63
     Surfaces
    0.61
    Activations Density 0.216%

    No Known Activations