© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15871
    Prev
    Next
    INDEX
    Explanations

    references to items, devices, or concepts relevant to household or office environments, specifically focusing on their functions and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laubt
    -0.46
    cydow
    -0.44
     nawr
    -0.42
     الرياضيه
    -0.41
     ổ
    -0.41
    étaires
    -0.40
    PrototypeOf
    -0.40
    LookAnd
    -0.39
     sécurisé
    -0.39
    WAY
    -0.39
    POSITIVE LOGITS
    balleur
    0.68
    aarrggbb
    0.66
    principalColumn
    0.55
    rungsseite
    0.54
     onOptions
    0.48
     Administrativna
    0.48
    ########.
    0.45
    gadget
    0.43
    @[+][
    0.41
     estekak
    0.41
    Activations Density 1.105%

    No Known Activations