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. 0-GEMMASCOPE-RES-16K
    6. 6932
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related terms, especially those related to data structure management and error handling

    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
    assertArray
    -0.54
    noons
    -0.47
    ",$
    -0.46
    )":
    -0.45
    telser
    -0.44
    `;
    
    -0.44
    !";
    -0.44
    ?";
    -0.44
    壤
    -0.44
     Cushing
    -0.43
    POSITIVE LOGITS
    Становништво
    0.81
     harmless
    0.65
    PerformLayout
    0.65
    bewerken
    0.62
     الرياضيه
    0.62
    دانشنامهٔ
    0.61
     Bind
    0.61
     تانيه
    0.60
    simpleType
    0.58
     innocent
    0.57
    Activations Density 2.222%

    No Known Activations