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. 16-GEMMASCOPE-RES-16K
    6. 6426
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes related to datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or data snippets

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers or syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++]=
    -0.69
    :],
    -0.59
    ]]
    
    -0.59
     en
    -0.58
    }));
    
    -0.55
    ()));
    
    -0.54
    ']?>
    -0.54
    )");
    
    -0.53
    ()))
    
    -0.53
    ()].
    -0.53
    POSITIVE LOGITS
    AndEndTag
    0.75
     ModelExpression
    0.73
    featureID
    0.73
    yntaxException
    0.69
    存于互联网档案馆
    0.63
    tidaknya
    0.61
     vermelhas
    0.58
     AssemblyCompany
    0.58
    LLocation
    0.57
    UpInside
    0.57
    Activations Density 1.409%

    No Known Activations