© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 92800
    Prev
    Next
    INDEX
    Explanations

    clinical terms and measurements related to diseases and patient outcomes

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

    arthropathy outcomes and adverse events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Majefty
    -0.53
    __':
    -0.50
     ſmall
    -0.47
    存于互联网档案馆
    -0.47
     deſt
    -0.47
    __':
    
    -0.46
    UrlResolution
    -0.46
    ſelf
    -0.45
     purpoſe
    -0.45
    __":
    -0.44
    POSITIVE LOGITS
     ≥
    0.60
     confirmed
    0.54
     declared
    0.51
     classified
    0.51
     defined
    0.50
     recorded
    0.48
     eligible
    0.47
    ≥
    0.47
    defined
    0.47
     predefined
    0.46
    Activations Density 1.091%

    No Known Activations