© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3912
    Prev
    Next
    INDEX
    Explanations

    keywords related to optical and genetic concepts

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

    ending in "-ic", "-astic", or related to sight/vision

    np_acts-logits-general · gemini-2.0-flash

    optic nerve, cosmic explorer, graphic design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
    Życiorys
    -0.72
    webElementXpaths
    -0.69
    onora
    -0.64
    tvguidetime
    -0.64
    pieces
    -0.64
    houses
    -0.63
    --]
    -0.60
    ApiOperation
    -0.60
    AsUp
    -0.59
    heri
    -0.59
    POSITIVE LOGITS
    ally
    1.77
    ALLY
    1.42
    amente
    0.93
    all
    0.88
    ITY
    0.85
    idad
    0.81
    ity
    0.77
    als
    0.76
    zny
    0.73
    acy
    0.70
    Activations Density 0.556%

    No Known Activations