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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6585
    Prev
    Next
    INDEX
    Explanations

    references to face-to-face interactions or interviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.60
    Tikang
    -0.50
    CPtr
    -0.47
    Rüyada
    -0.45
    webElementXpaths
    -0.45
     okuyayım
    -0.44
    thâu
    -0.42
    :✨
    -0.41
     isNameExpr
    -0.41
    IndentedString
    -0.41
    POSITIVE LOGITS
    tious
    0.84
    tiously
    0.78
    mask
    0.75
    lifted
    0.67
    masks
    0.67
    lifts
    0.65
    lift
    0.61
     mask
    0.59
     masks
    0.59
    plate
    0.57
    Activations Density 0.158%

    No Known Activations