© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55549
    Prev
    Next
    INDEX
    Explanations

    instances of the word "like."

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

    user preferences or comparisons

    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
     ſind
    -0.88
    
    -0.84
    RTSC
    -0.83
     defaultstate
    -0.78
    setVerticalGroup
    -0.78
    RenderAtEndOf
    -0.77
     queſta
    -0.77
    prepareStatement
    -0.76
     snippetHide
    -0.76
    UseVisualStyle
    -0.73
    POSITIVE LOGITS
    0
    0.56
    1
    0.47
    [toxicity=0]
    0.44
    2
    0.40
    s
    0.39
     table
    0.38
     system
    0.38
     customer
    0.37
     Customer
    0.36
     user
    0.36
    Activations Density 0.006%

    No Known Activations