© 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. 6749
    Prev
    Next
    INDEX
    Explanations

    words related to actions, particularly those indicating interaction or status

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

    Follows the word "where"

    np_acts-logits-general · gemini-2.0-flash

    where things are

    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
    thebibliography
    -0.36
    λευτα
    -0.35
     Sélectionnez
    -0.35
    édrale
    -0.34
    Còn
    -0.34
     Ajoutez
    -0.33
    Reich
    -0.33
     مواليد
    -0.32
    ientôt
    -0.32
    각주
    -0.32
    POSITIVE LOGITS
     where
    0.74
     где
    0.71
    where
    0.70
     donde
    0.68
     ahol
    0.66
    NameInMap
    0.64
     όπου
    0.63
    SharedCtor
    0.58
    WHERE
    0.58
     जहां
    0.58
    Activations Density 0.265%

    No Known Activations