© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13980
    Prev
    Next
    INDEX
    Explanations

    terms related to technical components and measurements within a scientific or engineering context

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

    mathematical notation and variables in equations and formulas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    лтамалар
    -0.83
    MessageTagHelper
    -0.77
    rungsseite
    -0.71
    WaitGroup
    -0.69
    styleType
    -0.68
    oa̍t
    -0.68
    MethodManager
    -0.63
     MainAxisSize
    -0.63
    FunctionFlags
    -0.63
    PreferredItem
    -0.63
    POSITIVE LOGITS
     Officials
    0.35
     fixed
    0.35
     officials
    0.34
    mybatisplus
    0.32
    conocimiento
    0.31
     prescribed
    0.31
    Officials
    0.30
    JsonResponse
    0.29
     تع
    0.29
     Prü
    0.28
    Activations Density 1.544%

    No Known Activations