© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 11766
    Prev
    Next
    INDEX
    Explanations

    references to size, particularly the concept of "small" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pygame
    -0.47
     ser
    -0.47
     rate
    -0.47
     pygame
    -0.46
     suit
    -0.45
     goal
    -0.45
     Tur
    -0.44
     scene
    -0.44
     ta
    -0.43
     volume
    -0.43
    POSITIVE LOGITS
    èdia
    0.72
     MainAxisSize
    0.67
    Small
    0.66
    RectangleBorder
    0.62
     vloer
    0.60
    posób
    0.60
     Small
    0.60
     zijne
    0.59
     ब्रेकडाउन
    0.59
    neſs
    0.58
    Activations Density 0.206%

    No Known Activations