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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6846
    Prev
    Next
    INDEX
    Explanations

    elements related to event handling in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Matrix
    -0.49
     Cowell
    -0.48
     matrix
    -0.46
     oprot
    -0.45
    duct
    -0.44
     NSString
    -0.44
    setTransform
    -0.43
    hems
    -0.43
    EndGlobalSection
    -0.43
     indu
    -0.43
    POSITIVE LOGITS
    ActionEvent
    0.86
    出版年
    0.81
    )");
    
    0.70
    ]})
    0.68
    principalColumn
    0.67
    "):
    
    0.63
    })`
    0.62
    Filmografia
    0.62
    IBAction
    0.61
    équi
    0.61
    Activations Density 0.079%

    No Known Activations