Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 52462
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strike" and its variations

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

    strike, strikes, struck

    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
    pidou
    -0.65
    tableFuture
    -0.62
     Caves
    -0.62
     FetchType
    -0.59
    wps
    -0.59
     FormsModule
    -0.59
    acap
    -0.59
     NavController
    -0.57
     CEC
    -0.57
     momo
    -0.56
    POSITIVE LOGITS
     strike
    1.02
     Strike
    0.99
    Strike
    0.94
    strike
    0.89
     strikes
    0.73
     struck
    0.65
     Schlag
    0.64
     huelga
    0.61
     striker
    0.60
     Strikes
    0.60
    Activations Density 0.010%

    No Known Activations