© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5841
    Prev
    Next
    INDEX
    Explanations

    code-related terms and commands related to API requests or programming structures

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

    programming or code-related tokens, particularly method names and variables.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     ModelExpression
    -0.65
     gradova
    -0.49
    RotationOrder
    -0.47
    iredo
    -0.45
    culously
    -0.45
    EndContext
    -0.44
    ngrx
    -0.44
     onCancelled
    -0.43
     REX
    -0.43
    ckså
    -0.43
    POSITIVE LOGITS
     oprot
    0.45
    RenderAtEndOf
    0.40
     fér
    0.37
    -------
    0.36
    
    0.35
     istore
    0.33
    ItemBackground
    0.32
    ValueGenerated
    0.32
    Alone
    0.31
    WebVitals
    0.31
    Activations Density 0.749%

    No Known Activations