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. 20-GEMMASCOPE-RES-16K
    6. 2339
    Prev
    Next
    INDEX
    Explanations

    financial figures and monetary values

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

    Numbers or number-like words

    np_acts-logits-general · gemini-2.0-flash

    numbers and comma separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.51
     Marat
    -0.50
    withIdentifier
    -0.48
    jsxFileName
    -0.47
     nawr
    -0.47
    verifyException
    -0.47
    digde
    -0.47
     Hercules
    -0.46
     FSB
    -0.46
     musicales
    -0.46
    POSITIVE LOGITS
    NamedQueries
    0.66
    TemporalType
    0.61
    artamento
    0.60
    ConstraintMaker
    0.57
    šinou
    0.56
    WireFormat
    0.56
    MemoryWarning
    0.55
    hoga
    0.55
    ffine
    0.54
     kaarangay
    0.53
    Activations Density 0.190%

    No Known Activations