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. 21-GEMMASCOPE-RES-16K
    6. 6591
    Prev
    Next
    INDEX
    Explanations

    error handling and logging functionality in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xna
    -0.54
     okuyayım
    -0.53
    readValue
    -0.48
    Superficie
    -0.48
    ole
    -0.46
    acağına
    -0.46
    StatusOK
    -0.46
    neos
    -0.46
    ///</
    -0.45
     cán
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.89
    ChildScrollView
    0.77
     SqlDbType
    0.63
    UpInside
    0.62
    AnchorStyles
    0.62
     مشين
    0.61
     console
    0.60
    encodeWith
    0.60
     ProtoMessage
    0.58
    errHandler
    0.57
    Activations Density 0.058%

    No Known Activations