© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8153
    Prev
    Next
    INDEX
    Explanations

    mentions of film directors and their works

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

    "coach" or "director"

    np_acts-logits-general · gemini-2.0-flash

    coach or director names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    rxjs
    -0.56
    INSEE
    -0.55
    principalColumn
    -0.51
     Pristupljeno
    -0.50
     Paglinawan
    -0.49
     Player
    -0.49
    appé
    -0.49
    ommen
    -0.49
     TextAppearance
    -0.48
     Distribute
    -0.48
    POSITIVE LOGITS
     coach
    1.55
     Coach
    1.30
    coach
    1.29
     coaches
    1.28
    Coach
    1.26
     COACH
    1.20
     coaching
    1.18
    COACH
    1.15
     director
    1.12
     coached
    1.05
    Activations Density 0.194%

    No Known Activations