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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12687
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific structuring and spatial relationships in experimentation

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

    Square or triangular lattices/grids

    np_acts-logits-general · gemini-2.0-flash

    geometric grids and lattices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.45
     invitación
    -0.37
     Unterhaltung
    -0.36
     čierna
    -0.36
     kennis
    -0.35
     afges
    -0.35
    spesies
    -0.35
    plom
    -0.34
     redacción
    -0.34
    請繼續往下閱讀
    -0.34
    POSITIVE LOGITS
     grid
    1.55
     grids
    1.41
     Grid
    1.23
    grid
    1.20
    Grid
    1.09
     GRID
    1.07
    grids
    1.06
     lattice
    0.96
     spacing
    0.95
     mesh
    0.92
    Activations Density 1.193%

    No Known Activations