© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6267
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure

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

    code-related terms, particularly header files and system-level programming constructs.

    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
    Personendaten
    -1.21
    bootstrapcdn
    -1.02
     ModelExpression
    -1.01
    parsedMessage
    -0.96
     kasarigan
    -0.96
    RenderAtEndOf
    -0.92
     queſta
    -0.84
    MLLoader
    -0.84
    LookAnd
    -0.80
    WriteBarrier
    -0.80
    POSITIVE LOGITS
     
    0.59
    1
    0.57
    2
    0.56
    8
    0.54
     extra
    0.54
    Extra
    0.51
    m
    0.51
    extra
    0.51
    3
    0.50
    lys
    0.50
    Activations Density 0.086%

    No Known Activations