© 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. 28-GEMMASCOPE-RES-16K
    11. 3920
    Prev
    Next
    INDEX
    Explanations

    phrases indicating liability and responsibility related to content and transactions

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

    Liability, responsibility, or consequences

    np_acts-logits-general · gemini-2.0-flash

    responsibility for damages and repairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fprintf
    -0.38
    格
    -0.38
    Lage
    -0.35
    agh
    -0.34
     gro
    -0.34
    sam
    -0.33
    ictwo
    -0.32
     favoured
    -0.32
    paw
    -0.31
     advantage
    -0.31
    POSITIVE LOGITS
    StoryboardSegue
    0.67
    EndInit
    0.63
     actions
    0.62
     consequences
    0.61
     decisions
    0.59
     mistakes
    0.57
     daños
    0.57
     actes
    0.57
     conséquences
    0.57
     conseguenze
    0.56
    Activations Density 0.344%

    No Known Activations