© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12185
    Prev
    Next
    INDEX
    Explanations

    the beginning of programming code or markup that indicates structure and data definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.41
     intptr
    -0.34
     […]
    -0.33
    Autoritní
    -0.32
     ویکی‌پدی
    -0.32
    Fordítás
    -0.31
    قایناق‌لار
    -0.30
     this
    -0.30
     právě
    -0.30
    İstinadlar
    -0.29
    POSITIVE LOGITS
    MigrationBuilder
    0.75
    AnchorStyles
    0.67
    GEBURTS
    0.65
    Portail
    0.60
    pexpr
    0.60
    tdb
    0.60
    andExpect
    0.59
    proofing
    0.59
    AnimationsModule
    0.59
    ➌
    0.59
    Activations Density 0.748%

    No Known Activations