© 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. 10509
    Prev
    Next
    INDEX
    Explanations

    references to processes involving flow and movement through different mediums

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

    trajectories or paths where something moves through or past something else.

    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
    ronpa
    -0.35
     disponibilités
    -0.35
    useEffect
    -0.34
     declarative
    -0.34
     grunn
    -0.33
     Públicas
    -0.33
     pertumbuhan
    -0.33
     føl
    -0.33
     prieten
    -0.32
     tương
    -0.32
    POSITIVE LOGITS
     through
    0.97
    through
    0.95
    Through
    0.87
     Through
    0.84
     THROUGH
    0.82
     passes
    0.81
    thru
    0.81
    Thru
    0.80
    ผ่าน
    0.80
     thru
    0.76
    Activations Density 0.192%

    No Known Activations