© 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. 20-GEMMASCOPE-RES-16K
    11. 16288
    Prev
    Next
    INDEX
    Explanations

    terminologies related to surgical procedures and patient care in a medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or medical terminology related to procedures, operations, and professional work contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.40
    EDEFAULT
    -0.40
    querque
    -0.37
    rawDesc
    -0.36
     brave
    -0.35
     terciopelo
    -0.35
     Greenwood
    -0.35
     term
    -0.35
     no
    -0.35
     ever
    -0.35
    POSITIVE LOGITS
     otomatig
    0.75
     ब्रेकडाउन
    0.71
    Diweddarwch
    0.54
    
    0.53
     MonoBehaviour
    0.49
    gameserver
    0.48
    bestos
    0.48
    mobileqq
    0.48
     queſta
    0.47
    новниш
    0.46
    Activations Density 1.413%

    No Known Activations