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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6478
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "strike" and its variants, indicating references to hitting or attacking actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.71
     }}"></
    -0.63
    tagHelperRunner
    -0.61
    )");
    
    -0.61
     ddelweddau
    -0.59
    }]
    
    -0.57
    #
    
    -0.56
    )')
    -0.56
    }));
    
    -0.55
    ManagedBean
    -0.55
    POSITIVE LOGITS
     strike
    0.89
    strike
    0.87
     Strike
    0.85
     strikes
    0.84
     struck
    0.79
    Strike
    0.77
    scene
    0.76
     Strikes
    0.75
    destruction
    0.72
    struck
    0.72
    Activations Density 0.170%

    No Known Activations