© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15870
    Prev
    Next
    INDEX
    Explanations

    mentions of marine life, specifically sharks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adap
    -0.39
    Strategic
    -0.38
    ajaj
    -0.37
    Universal
    -0.36
     universal
    -0.36
     Kemal
    -0.36
    沿革
    -0.35
     Universal
    -0.35
     devi
    -0.35
    Selena
    -0.35
    POSITIVE LOGITS
     sightings
    0.57
    SequentialGroup
    0.56
    tvguidetime
    0.50
    ChildScrollView
    0.48
    entification
    0.47
    scribers
    0.47
     שוליים
    0.46
    Rüyada
    0.45
    encounter
    0.45
    observations
    0.45
    Activations Density 0.263%

    No Known Activations