© 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. 6128
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to scientific procedures and methodologies, particularly in the context of chemical or biological analyses

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

    technical/scientific language related to research procedures, measurements, and data processing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    words or phrases indicating purpose, often activating on "for" followed by a description of intended use or goal.

    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
     ligiloj
    -0.54
     MainAxisSize
    -0.53
     GenerationType
    -0.50
    ſelf
    -0.50
     betweenstory
    -0.47
    waitKey
    -0.46
     NavController
    -0.44
    قایناق‌لار
    -0.44
    Rohy
    -0.44
     transfieras
    -0.44
    POSITIVE LOGITS
    verläs
    0.36
     dals
    0.35
     wę
    0.34
    演
    0.33
     paš
    0.33
    jarati
    0.32
    Референце
    0.32
     mourut
    0.32
     vervolgens
    0.31
     then
    0.30
    Activations Density 0.765%

    No Known Activations