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. 6091
    Prev
    Next
    INDEX
    Explanations

    URLs and references related to programming and API documentation

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

    Numbers found within URLs or identifiers

    np_acts-logits-general · gemini-2.0-flash

    URL identifiers or codes

    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
    IVEREF
    -0.78
     >=",
    -0.77
     дописавши
    -0.69
     AssemblyVersion
    -0.66
    GraphicsUnit
    -0.63
    AutoField
    -0.63
     onPostExecute
    -0.62
    VersionUID
    -0.60
    PullParser
    -0.60
    resizingMask
    -0.59
    POSITIVE LOGITS
     officinalis
    0.47
    海道
    0.45
    findpost
    0.45
    postos
    0.43
    tagHelperRunner
    0.43
    knię
    0.42
     colspan
    0.41
    蒡
    0.41
    ļa
    0.41
     чер
    0.40
    Activations Density 0.340%

    No Known Activations