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. 24-GEMMASCOPE-RES-16K
    6. 2258
    Prev
    Next
    INDEX
    Explanations

    mentions of academic roles and acknowledgments of contributions in research

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

    Name after a comma or title

    np_acts-logits-general · gemini-2.0-flash

    names following titles or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     financières
    -0.74
    CppMethod
    -0.69
    AnchorStyles
    -0.64
    :"
    -0.62
     protoimpl
    -0.62
     bénéfices
    -0.61
    AccessorTable
    -0.60
    (!__
    -0.60
    DockStyle
    -0.60
    ImageContext
    -0.59
    POSITIVE LOGITS
    <bos>
    0.79
     esternos
    0.59
    etheless
    0.56
    )}]{
    0.56
    utenant
    0.54
    '},
    
    0.53
    romeda
    0.52
    createCanvas
    0.51
    cknow
    0.50
    $.
    
    0.50
    Activations Density 0.341%

    No Known Activations