© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5373
    Prev
    Next
    INDEX
    Explanations

    references to risks and dangers related to high-stakes actions or stunts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Metcalf
    -0.50
     specific
    -0.50
    )['
    -0.50
     Bul
    -0.49
    ylvania
    -0.47
     shift
    -0.47
     stop
    -0.46
    ipat
    -0.46
    Bul
    -0.45
     AssemblyProduct
    -0.45
    POSITIVE LOGITS
     acrob
    0.95
     acrobat
    0.77
     stunts
    0.77
     vertigo
    0.77
    Acro
    0.76
     aérea
    0.71
    apunov
    0.70
     UIImage
    0.70
     parachute
    0.69
    typeorm
    0.68
    Activations Density 0.224%

    No Known Activations