Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 5306
    Prev
    Next
    INDEX
    Explanations

    return statements and associated control flow in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithEmail
    -0.67
     hipó
    -0.67
    selho
    -0.59
     lunghe
    -0.56
     tekem
    -0.56
    GeoNames
    -0.56
    werb
    -0.56
    PageContext
    -0.54
     thrush
    -0.54
     sposa
    -0.53
    POSITIVE LOGITS
    {}{}
    0.79
     }}"></
    0.78
     >=",
    0.73
     lenker
    0.69
    twimg
    0.69
     <=",
    0.68
    ranton
    0.68
     ProtoMessage
    0.65
    (!__
    0.65
    日閲覧
    0.64
    Activations Density 0.034%

    No Known Activations