© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 112011
    Prev
    Next
    INDEX
    Explanations

    descriptions of flat or planar shapes and structures

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

    flatness and dimensionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zo
    -0.37
     Sub
    -0.34
    WriteAttribute
    -0.33
     проб
    -0.33
    SqlClient
    -0.33
    joint
    -0.32
    irk
    -0.32
     Rede
    -0.31
    ỉnh
    -0.31
     voegen
    -0.31
    POSITIVE LOGITS
     flat
    0.78
     flattened
    0.72
     FLAT
    0.70
     flattening
    0.69
    Flat
    0.68
     flatten
    0.68
    flat
    0.67
    扁平
    0.63
     flats
    0.61
    abetes
    0.61
    Activations Density 0.158%

    No Known Activations