© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9010
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or conversation starters, particularly question words or greetings in both English and Chinese.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    questions and inquiries that start with "how" or "which."

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

    Follows "how" or "which"

    np_acts-logits-general · gemini-2.0-flash

    how or which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     et
    -0.33
    які
    -0.27
    verwijspagina
    -0.26
     يتيمه
    -0.26
     كومونز
    -0.26
     ब्रेकडाउन
    -0.25
    úgó
    -0.25
     etc
    -0.24
     Users
    -0.23
    HtmlAttribute
    -0.23
    POSITIVE LOGITS
     Infór
    0.73
    iſchen
    0.66
     Paglinawan
    0.66
     beſte
    0.66
    ſſung
    0.65
    <unused41>
    0.65
     queſta
    0.65
    səhifə
    0.64
    <unused51>
    0.64
    <unused28>
    0.64
    Activations Density 1.361%

    No Known Activations