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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2398
    Prev
    Next
    INDEX
    Explanations

    terms associated with the severity of medical conditions and injuries

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

    "severe" or "severity"

    np_acts-logits-general · gemini-2.0-flash

    level of severity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.68
     fieldNum
    -0.61
     wireType
    -0.56
    toplankton
    -0.54
    GetEnumerator
    -0.53
    StructEnd
    -0.52
     quête
    -0.52
    AnchorStyles
    -0.52
    ledad
    -0.50
    silien
    -0.49
    POSITIVE LOGITS
     severe
    1.31
    Severe
    1.11
     Severe
    1.10
     severity
    1.09
    severe
    1.09
     serious
    1.04
     Severity
    0.95
    SEVERE
    0.91
    Severity
    0.87
     worse
    0.86
    Activations Density 0.581%

    No Known Activations