© 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. 38-GEMMASCOPE-RES-16K
    11. 7112
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific methodologies and regulatory terminology related to medical applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.46
    webElementXpaths
    -0.40
    المناصب
    -0.39
    rawDesc
    -0.37
    rrggbb
    -0.36
    FML
    -0.36
    Rhestr
    -0.35
    blings
    -0.34
    Gön
    -0.34
     MCG
    -0.33
    POSITIVE LOGITS
     EA
    1.34
     SA
    1.32
     FA
    1.31
     PA
    1.31
     BA
    1.30
     VA
    1.29
     TA
    1.27
     CA
    1.26
     RA
    1.25
     JA
    1.24
    Activations Density 1.535%

    No Known Activations