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 - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28381
    Prev
    Next
    INDEX
    Explanations

    monetary symbols and related references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     justific
    -0.48
     vok
    -0.47
    werde
    -0.46
    HomeAsUpEnabled
    -0.46
    ocytosis
    -0.46
     canadien
    -0.46
    béco
    -0.45
    preventDefault
    -0.45
    ixels
    -0.45
    racycline
    -0.44
    POSITIVE LOGITS
    Билгалдахарш
    0.84
    ngdoc
    0.79
     ***!
    0.78
    ThroughAttribute
    0.75
    :✨
    0.75
     ویکی‌پدیا
    0.74
     InputDecoration
    0.69
    كويكب
    0.68
    writeFieldEnd
    0.66
    AndroidJUnit
    0.66
    Activations Density 0.022%

    No Known Activations