© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12633
    Prev
    Next
    INDEX
    Explanations

    words that indicate uncertainty or probability

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

    "probably"

    np_acts-logits-general · gemini-2.0-flash

    probably

    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
     BoxFit
    -0.50
    WriteLiteral
    -0.46
     Audiodateien
    -0.46
     Initialized
    -0.45
     openings
    -0.45
    IsPostBack
    -0.45
    UserScript
    -0.44
     HasFactory
    -0.44
    Sitemap
    -0.43
     viens
    -0.42
    POSITIVE LOGITS
    probably
    0.84
     probably
    0.82
    Probably
    0.77
     Probably
    0.75
    mostly
    0.65
     likely
    0.64
     mostly
    0.63
     للاسماء
    0.63
    bably
    0.63
     waarschijnlijk
    0.60
    Activations Density 0.156%

    No Known Activations