© 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. 35-GEMMASCOPE-RES-16K
    11. 14408
    Prev
    Next
    INDEX
    Explanations

    highly activated biological processes or effects related to compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.58
    MigrationBuilder
    -0.52
    simpleType
    -0.42
     doomed
    -0.42
    IVEREF
    -0.41
     Exposure
    -0.40
    朱印
    -0.40
    Reak
    -0.40
     infe
    -0.40
    DockStyle
    -0.40
    POSITIVE LOGITS
     anti
    1.00
     antiviral
    0.74
     potent
    0.73
     antic
    0.70
     antibacterial
    0.70
     analgesic
    0.69
     propriétés
    0.66
     therapeutic
    0.66
     Anti
    0.65
    Anti
    0.65
    Activations Density 1.558%

    No Known Activations