© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16377
    Prev
    Next
    INDEX
    Explanations

    references to the roles and importance of various professionals and mechanisms in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.40
    twimg
    -0.38
    MigrationBuilder
    -0.38
    ffindor
    -0.38
    štu
    -0.35
    modity
    -0.34
    intree
    -0.33
    ちん
    -0.33
    Espèce
    -0.32
    actéristi
    -0.32
    POSITIVE LOGITS
     role
    3.73
     roles
    3.20
    role
    3.11
     Role
    3.02
    Role
    2.94
     ROLE
    2.83
     Roles
    2.67
    roles
    2.59
    ROLE
    2.59
     rôle
    2.58
    Activations Density 0.816%

    No Known Activations