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. 5-GEMMASCOPE-RES-16K
    6. 3944
    Prev
    Next
    INDEX
    Explanations

    units of measurement and statistical data attributes in the context of scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errHandler
    -0.78
    __":
    
    -0.77
    }`).
    -0.76
    __':
    
    -0.76
    :+:
    -0.76
    "]];
    -0.72
    sizeCache
    -0.71
     مرئيه
    -0.69
    ElementException
    -0.65
    ."));
    -0.65
    POSITIVE LOGITS
     verba
    0.47
    upuncture
    0.46
    UrlEncoded
    0.45
    УДК
    0.44
     bothering
    0.43
    NewUrlParser
    0.42
     glandular
    0.42
     daring
    0.41
    Seconds
    0.41
     dared
    0.41
    Activations Density 0.408%

    No Known Activations