© 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. 108504
    Prev
    Next
    INDEX
    Explanations

    expressions and variations of the word "gentle."

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

    gentle to describe actions or things

    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
     number
    -0.48
     Wikimedijinoj
    -0.45
     quoi
    -0.44
     situation
    -0.44
     Affaires
    -0.43
     Existenz
    -0.41
     stör
    -0.41
    话
    -0.40
     bevis
    -0.40
     corrida
    -0.40
    POSITIVE LOGITS
    Gentle
    1.14
     Gentle
    1.13
    gentle
    1.02
     gentle
    1.01
     GENTLE
    0.96
     gentler
    0.90
     gently
    0.88
     Gently
    0.87
    entle
    0.79
     gentleness
    0.73
    Activations Density 0.003%

    No Known Activations