© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    terms related to light and its properties

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

    technical or scientific terms and abbreviations in specialized domains.

    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
    WriteAttribute
    -0.49
    RenderAtEndOf
    -0.45
    
    -0.44
     muualla
    -0.40
    forName
    -0.38
    IGraphics
    -0.38
    ILON
    -0.38
     Debates
    -0.37
    iedades
    -0.36
    enumii
    -0.36
    POSITIVE LOGITS
     surla
    0.53
    ########.
    0.46
     gewo
    0.45
     quelqu
    0.43
     frutto
    0.41
    backed
    0.41
     murni
    0.41
     nicest
    0.40
    closest
    0.40
     backed
    0.40
    Activations Density 0.808%

    No Known Activations