© 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. 1-GEMMASCOPE-RES-16K
    11. 3220
    Prev
    Next
    INDEX
    Explanations

    terms related to early occurrences or interventions in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igneur
    -0.42
     hObject
    -0.40
    hadur
    -0.40
     Réponses
    -0.39
    ymbol
    -0.39
    ECONDS
    -0.38
    ighorn
    -0.37
    ifstream
    -0.36
    featureID
    -0.35
    LEncoder
    -0.35
    POSITIVE LOGITS
     early
    2.08
     late
    2.03
    early
    1.88
    late
    1.65
    Late
    1.62
     Late
    1.59
    Early
    1.55
     EARLY
    1.52
     LATE
    1.48
     Early
    1.46
    Activations Density 0.194%

    No Known Activations