© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13164
    Prev
    Next
    INDEX
    Explanations

    warnings or safety alerts related to medications

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

    medical safety warnings and instructions, particularly related to medication usage.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    warning messages and cautionary instructions in product or medical documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tweaked
    -0.50
     Tsch
    -0.45
     clunky
    -0.44
     squishy
    -0.41
     tweaks
    -0.40
     overkill
    -0.40
     tweaking
    -0.39
    Välislingid
    -0.38
     conco
    -0.38
     apocalypse
    -0.38
    POSITIVE LOGITS
     należy
    0.57
     WARNING
    0.55
    省市镇
    0.53
    WARNING
    0.52
    CAUTION
    0.50
     Operator
    0.50
    cyklopedia
    0.47
     operator
    0.47
     bedien
    0.47
    OPERATOR
    0.47
    Activations Density 0.376%

    No Known Activations