© 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. 76383
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bother."

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

    bothering or being bothered

    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
    issauga
    -0.63
    ędziesz
    -0.57
    ViewImports
    -0.56
     <=",
    -0.55
    __":
    
    -0.54
    imageshack
    -0.54
    ersonic
    -0.54
    __":
    -0.53
     Palau
    -0.52
    <?
    
    -0.50
    POSITIVE LOGITS
     bother
    0.95
     bothered
    0.85
     bothers
    0.79
     bothering
    0.78
     Matter
    0.56
    trouble
    0.54
    touch
    0.52
     Trouble
    0.52
     Disturb
    0.51
    trou
    0.50
    Activations Density 0.004%

    No Known Activations