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. 28390
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to derivatives

    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
    ContentAlignment
    -0.58
    httphttps
    -0.52
    \{\\
    -0.52
     متعلقه
    -0.48
     drinker
    -0.47
    toThrow
    -0.46
    tenths
    -0.46
    BaseAdapter
    -0.44
    icap
    -0.43
    ihnachts
    -0.43
    POSITIVE LOGITS
     саны
    0.72
     propOrder
    0.69
     ErrIntOverflow
    0.60
    aarrggbb
    0.60
     OMIT
    0.56
    IndentedString
    0.56
     hés
    0.56
    setVerticalGroup
    0.56
     AssemblyTitle
    0.54
    elding
    0.54
    Activations Density 0.320%

    No Known Activations