© 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. 9-GEMMASCOPE-RES-131K
    11. 19943
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fought" and its variations in various contexts

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

    fought or fighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hyperlink
    -0.42
     uLocal
    -0.41
    sidemargin
    -0.39
    ℳ
    -0.37
     serial
    -0.36
     Laub
    -0.35
     vacancy
    -0.35
     consignment
    -0.35
     Macro
    -0.35
    못
    -0.35
    POSITIVE LOGITS
     fought
    1.43
     fighting
    1.29
    fought
    1.23
    Fighting
    1.18
    fighting
    1.18
     fight
    1.14
     Fighting
    1.09
     fights
    1.08
     FIGHT
    1.08
    fight
    1.06
    Activations Density 0.008%

    No Known Activations