© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 66250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "expose" and its variations related to revealing or making something visible

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

    revealing or making vulnerable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.59
     برانيه
    -0.57
     argint
    -0.54
     líquida
    -0.53
     ainfi
    -0.52
     resultList
    -0.52
    WidgetItem
    -0.50
    хьтан
    -0.50
    MessageOf
    -0.49
     engraçadas
    -0.49
    POSITIVE LOGITS
     exposure
    1.09
     expose
    1.04
    Expose
    1.03
    Exposed
    1.02
     exposed
    1.02
     EXPOSURE
    1.02
    Exposure
    1.00
     Exposure
    0.99
    expose
    0.99
    exposed
    0.97
    Activations Density 0.014%

    No Known Activations