© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3844
    Prev
    Next
    INDEX
    Explanations

    references to operational code and programming constructs related to thread management

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

    Code snippets and related terms

    np_acts-logits-general · gemini-2.0-flash

    switch ( field, 0 )

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.48
    yarnpkg
    -0.44
    minecraftforge
    -0.42
     propOrder
    -0.42
    InlineData
    -0.42
    setVerticalGroup
    -0.42
    yelitis
    -0.42
    rungsseite
    -0.42
     addItem
    -0.42
    tvguidetime
    -0.42
    POSITIVE LOGITS
     corresponding
    0.55
    corresponding
    0.53
     Corresponding
    0.50
     corrispond
    0.46
     correspondant
    0.44
    byId
    0.43
    BitmapFactory
    0.43
    ById
    0.43
    ByID
    0.43
     berdasarkan
    0.42
    Activations Density 0.279%

    No Known Activations