© 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. 7657
    Prev
    Next
    INDEX
    Explanations

    comparative terms related to body parts or sides

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

    Left, right, or opposite sides

    np_acts-logits-general · gemini-2.0-flash

    left, right, other, sides

    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
    parsedMessage
    -0.52
    ographia
    -0.50
     insuffisamment
    -0.50
     Reſ
    -0.47
    LEncoder
    -0.47
    findpost
    -0.46
    rungsseite
    -0.46
    
    -0.45
    pecabe
    -0.45
    Hentet
    -0.44
    POSITIVE LOGITS
     side
    0.88
     sides
    0.66
    side
    0.65
     halves
    0.63
     half
    0.62
     SIDE
    0.59
     hemisphere
    0.57
     Hälfte
    0.57
     Side
    0.54
    Side
    0.54
    Activations Density 0.407%

    No Known Activations