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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 77551
    Prev
    Next
    INDEX
    Explanations

    references to championship cups in sports contexts

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

    sports cup competitions

    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
    hline
    -0.40
     “
    -0.39
    ]");
    -0.37
     ";
    
    -0.37
     Weiss
    -0.37
     Shar
    -0.37
     Maurice
    -0.37
    ztő
    -0.37
    </blockquote>
    -0.37
     Algo
    -0.36
    POSITIVE LOGITS
     Cup
    2.75
    Cup
    2.59
     cup
    2.39
     CUP
    2.23
    cup
    2.19
     Cups
    2.03
    CUP
    1.92
     cups
    1.86
    cups
    1.63
    杯
    1.60
    Activations Density 0.007%

    No Known Activations