© 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. 2504
    Prev
    Next
    INDEX
    Explanations

    sequences and relationships in events or concepts

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

    passive voice verb forms like "preceded", "followed", "dominated", "governed".

    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
     endfor
    -0.47
    currentTarget
    -0.43
     Seaside
    -0.40
     into
    -0.39
     unde
    -0.39
     Geden
    -0.38
     Jonas
    -0.38
    ニーカー
    -0.38
    Hire
    -0.38
    င်း
    -0.38
    POSITIVE LOGITS
     propOrder
    0.81
    bootstrapcdn
    0.80
     nahilalakip
    0.72
    AutoScaleMode
    0.60
     MainAxisSize
    0.57
    setVerticalGroup
    0.52
    reportWebVitals
    0.51
     BrowserModule
    0.51
     ModelRenderer
    0.50
     parseFrom
    0.49
    Activations Density 0.234%

    No Known Activations