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 - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28498
    Prev
    Next
    INDEX
    Explanations

    numerical references and legal case citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -0.88
    "],
    
    -0.79
    '],
    
    -0.75
    "))
    
    -0.75
    ")));
    
    -0.73
    '));
    
    -0.72
    '):
    
    -0.71
     pinulongan
    -0.70
    %"),
    -0.70
    enumi
    -0.69
    POSITIVE LOGITS
    EndContext
    0.61
     ProtoMessage
    0.57
    بوابة
    0.55
    лтамалар
    0.54
    AsUp
    0.53
     mengen
    0.49
    Portail
    0.46
    بینی
    0.46
    ArgsConstructor
    0.45
    tiembre
    0.45
    Activations Density 0.019%

    No Known Activations