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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1750
    Prev
    Next
    INDEX
    Explanations

    company names or corporate designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']")
    -0.71
    */;
    -0.70
     '-';
    -0.69
    '},
    
    -0.69
    ']],
    -0.68
    )$}
    -0.68
    }}}
    
    -0.68
    ;");
    -0.68
    "):
    
    -0.67
    ?")
    -0.67
    POSITIVE LOGITS
     Ltd
    1.05
     LLC
    0.95
     Inc
    0.88
     LTD
    0.83
    Ltd
    0.82
     Bhd
    0.81
    有限公司
    0.77
     ltd
    0.75
     المتحدة
    0.73
    SPATH
    0.71
    Activations Density 0.071%

    No Known Activations