© 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. 20-GEMMASCOPE-RES-16K
    6. 10728
    Prev
    Next
    INDEX
    Explanations

    references to technical processes and components in scientific literature

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

    technical specifications and descriptions in patents, academic papers, and product documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.47
     Италијани
    -0.46
     ويكيپيديا
    -0.35
    rawDesc
    -0.34
     Numerade
    -0.33
    ...@
    -0.32
     procé
    -0.31
    #+#
    -0.31
     diſt
    -0.31
    RTDA
    -0.30
    POSITIVE LOGITS
     podjela
    0.50
    zarchiwizowane
    0.49
    ENIE
    0.48
    LookAnd
    0.47
    :✨
    0.47
     Waray
    0.46
     textStatus
    0.45
    iego
    0.45
     MainAxisSize
    0.45
    icides
    0.45
    Activations Density 0.254%

    No Known Activations