© 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. 22-GEMMASCOPE-RES-16K
    11. 13963
    Prev
    Next
    INDEX
    Explanations

    references to various cell types and their behaviors, particularly adhesion and proliferation characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.53
     Wilkinson
    -0.49
     dritte
    -0.47
     baskılı
    -0.46
     Goodwin
    -0.46
     Gries
    -0.46
     other
    -0.45
     Bick
    -0.45
     Bogen
    -0.44
     principales
    -0.44
    POSITIVE LOGITS
     Cell
    1.15
    Cell
    1.14
     CELL
    1.08
     UITableViewCell
    1.08
    cell
    1.05
     Cells
    1.04
     cell
    1.01
    Cells
    0.97
    getCell
    0.95
    CELL
    0.94
    Activations Density 0.156%

    No Known Activations