© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13878
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fight" and related contexts of struggle or resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __))
    -0.64
     jScrollPane
    -0.63
     Jacobsen
    -0.62
    \"");
    -0.61
    ))));
    -0.61
    )");
    
    -0.60
     egli
    -0.59
     getSystem
    -0.58
     bekan
    -0.58
     TEC
    -0.57
    POSITIVE LOGITS
     fight
    1.56
    fight
    1.36
     Fight
    1.29
    Fight
    1.28
     FIGHT
    1.23
     fighting
    1.12
     fought
    1.08
    FIGHT
    1.05
     fights
    1.01
    Fighting
    1.01
    Activations Density 0.057%

    No Known Activations