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-2-9B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9
    Prev
    Next
    INDEX
    Explanations

    values and parameters related to graphical elements in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_17/width_16k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ChildScrollView
    -0.44
    󠁢
    -0.44
     nahilalakip
    -0.43
     <<<<<<<<<<<<<<
    -0.42
    เยอะ
    -0.40
     ffilmiau
    -0.39
    PyExc
    -0.39
    tableFuture
    -0.39
    setMinimumSize
    -0.39
     hadapan
    -0.38
    POSITIVE LOGITS
     CURIAM
    0.56
     disambiguazione
    0.52
    webElementXpaths
    0.48
    delwed
    0.46
    ViewFeatures
    0.46
    HideFlags
    0.46
    quick
    0.45
     produisons
    0.44
    ellido
    0.44
    انگلیسی
    0.43
    Activations Density 0.260%

    No Known Activations