© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9307
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss specific aspects or components of a larger topic

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

    Followed by "of" or a foreign language "some"

    np_acts-logits-general · gemini-2.0-flash

    some of the

    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
     Ganzen
    -0.55
    󠁢
    -0.51
     ویکی‌پدیای
    -0.50
     allemaal
    -0.49
    jsxFileName
    -0.45
    internalType
    -0.44
    RenderAtEndOf
    -0.43
     всеми
    -0.42
    forall
    -0.42
     everywhere
    -0.41
    POSITIVE LOGITS
     niektó
    0.71
     někter
    0.65
     بعضی
    0.64
     algunos
    0.64
     некоторые
    0.62
     niektor
    0.62
     Algunos
    0.62
    Algunos
    0.62
     Algunas
    0.61
     sommige
    0.61
    Activations Density 0.478%

    No Known Activations