© 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. 40-GEMMASCOPE-RES-16K
    6. 5412
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical conditions and their severity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.44
     commerciaux
    -0.39
    AutoModerator
    -0.38
     UserRepository
    -0.35
    enseits
    -0.35
     commer
    -0.35
     MainAxisSize
    -0.34
    rsiniz
    -0.34
     Supreme
    -0.33
     USGS
    -0.33
    POSITIVE LOGITS
     pathological
    0.64
     violations
    0.64
     Violations
    0.60
     pathologies
    0.59
     violation
    0.58
     défaite
    0.57
     pathology
    0.56
     violación
    0.56
    Viol
    0.56
    Violation
    0.56
    Activations Density 0.469%

    No Known Activations