© 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. 10-GEMMASCOPE-RES-16K
    11. 12844
    Prev
    Next
    INDEX
    Explanations

    qualitative descriptions and outlines in analyses or proofs

    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
     especialidad
    -0.40
    раздо
    -0.38
    
    -0.38
    GOTREF
    -0.37
    GeneratedValue
    -0.37
     exhaust
    -0.36
    unicaciones
    -0.36
    forhold
    -0.35
    migrationBuilder
    -0.35
     skuto
    -0.35
    POSITIVE LOGITS
    大致
    0.78
     cursory
    0.74
    Brief
    0.73
     vague
    0.70
     basic
    0.70
     rough
    0.69
     Rough
    0.68
     tentative
    0.68
     outlines
    0.68
     briefly
    0.67
    Activations Density 0.856%

    No Known Activations