© 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. 12675
    Prev
    Next
    INDEX
    Explanations

    actions and events, particularly focusing on circumstances involving people and their interactions

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

    Follows verbs of action or movement

    np_acts-logits-general · gemini-2.0-flash

    collecting or threatening

    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
     Autorizaciones
    -0.47
     nahilalakip
    -0.46
     useHistory
    -0.42
    skel
    -0.42
    FunctionFlags
    -0.41
    rousel
    -0.41
    ्रीय
    -0.40
    ħħ
    -0.40
    ôles
    -0.40
     institucional
    -0.40
    POSITIVE LOGITS
    AndEndTag
    0.64
     HasFactory
    0.50
    tvguidetime
    0.40
    dflare
    0.37
     }{@
    0.34
    Kjelder
    0.34
    گاب
    0.34
     appointment
    0.33
    WaitGroup
    0.32
    PerformLayout
    0.32
    Activations Density 0.310%

    No Known Activations