© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15272
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of doubt or uncertainty

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

    Contractions with "not"

    np_acts-logits-general · gemini-2.0-flash

    don't know/think

    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
     itſelf
    -0.55
    存于互联网档案馆
    -0.48
     estekak
    -0.46
    ScopeManager
    -0.46
    >();
    -0.46
    󠁿
    -0.46
    Coordonnées
    -0.45
     setId
    -0.44
     inputStream
    -0.44
     avena
    -0.42
    POSITIVE LOGITS
     wasnt
    0.69
     didnt
    0.65
     aint
    0.64
    حياته
    0.64
     fuckin
    0.60
     prolly
    0.58
     couldnt
    0.57
     shouldnt
    0.55
     doesnt
    0.54
     arent
    0.54
    Activations Density 0.193%

    No Known Activations