© 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. 13739
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or conditions for understanding complex situations

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

    Text after conjunctions or commas

    np_acts-logits-general · gemini-2.0-flash

    neither nor

    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
    expandindo
    -0.45
     lenker
    -0.40
    MemoryWarning
    -0.40
    хьтан
    -0.35
    Notae
    -0.33
     ķ
    -0.33
    Personendaten
    -0.32
    Personensuche
    -0.31
    AutoScaleMode
    -0.30
     máscaras
    -0.30
    POSITIVE LOGITS
     neither
    0.64
     nor
    0.62
     للاسماء
    0.61
    nor
    0.61
    neither
    0.60
    Neither
    0.56
     propOrder
    0.53
     Neither
    0.52
     Италијани
    0.52
    而是
    0.52
    Activations Density 0.774%

    No Known Activations