© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2376
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to effective medical practices or criteria

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

    well suited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     [
    -0.52
     officiels
    -0.49
     (
    -0.49
    insegna
    -0.47
    sizeCache
    -0.47
     ponta
    -0.46
    éges
    -0.45
    맙
    -0.44
    Élet
    -0.44
     richesse
    -0.44
    POSITIVE LOGITS
     suited
    1.42
    suited
    1.30
     suitable
    1.11
     unsuitable
    1.06
     suitability
    1.05
    suitable
    1.00
     suit
    0.99
     Suit
    0.99
     Suitable
    0.98
    Suitable
    0.95
    Activations Density 0.152%

    No Known Activations