© 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. 6640
    Prev
    Next
    INDEX
    Explanations

    transitional phrases that introduce summaries or clarifications

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

    transition phrases like "So" and other language signaling the start of a summary or explanation.

    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
     Lightboxes
    -0.55
    pendicular
    -0.51
    hasia
    -0.48
    calciatore
    -0.48
    merking
    -0.48
    entiment
    -0.47
    timation
    -0.46
    jsx
    -0.46
    ulman
    -0.44
    uscitation
    -0.44
    POSITIVE LOGITS
    So
    0.68
    Итак
    0.66
     So
    0.63
    FXML
    0.54
     Donc
    0.50
    Donc
    0.45
     Wherefore
    0.44
    Quindi
    0.43
    RenderAtEndOf
    0.43
    UnknownFields
    0.42
    Activations Density 0.103%

    No Known Activations