© 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. 11593
    Prev
    Next
    INDEX
    Explanations

    terms related to ecological and environmental factors

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

    after the word "habitat" or similar concepts

    np_acts-logits-general · gemini-2.0-flash

    habitat, outcome, and formula concepts

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    ings
    -0.69
    groups
    -0.64
     Gerichts
    -0.60
    nings
    -0.60
    WebElementEntity
    -0.59
    manship
    -0.57
    linge
    -0.54
    INGS
    -0.53
     Jans
    -0.52
    houses
    -0.50
    POSITIVE LOGITS
    naires
    0.86
    HtmlAttribute
    0.77
    Personendaten
    0.75
     Vitae
    0.75
    ViewFeatures
    0.73
     ―――――
    0.73
    osidad
    0.72
    ized
    0.70
     Baillargeon
    0.70
     itſelf
    0.69
    Activations Density 0.887%

    No Known Activations