© 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. 36-GEMMASCOPE-RES-16K
    11. 16066
    Prev
    Next
    INDEX
    Explanations

    mentions of regulatory authorities and their implications for clinical trials or market approvals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.66
    parsedMessage
    -0.64
    RectangleBorder
    -0.63
    sendRedirect
    -0.60
    openzeppelin
    -0.60
    PyTuple
    -0.58
     wireType
    -0.58
     ब्रेकडाउन
    -0.58
    OptionsMenu
    -0.57
    ViewImports
    -0.57
    POSITIVE LOGITS
     authorities
    1.59
     authority
    1.32
    authorities
    1.26
     Authorities
    1.19
     regulators
    1.19
    Authorities
    1.17
     autoridad
    1.17
     AUTHORITIES
    1.15
     autorité
    1.14
     autoridades
    1.12
    Activations Density 0.626%

    No Known Activations