© 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. 14508
    Prev
    Next
    INDEX
    Explanations

    references to organizations, collaborations, and regulatory entities related to healthcare and energy

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

    following "of," "by," or similar prepositions

    np_acts-logits-general · gemini-2.0-flash

    charity or company support

    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
    ModelAdmin
    -0.82
    PMailer
    -0.74
    IntoConstraints
    -0.71
     للمعارف
    -0.70
     ModelExpression
    -0.69
    ThroughAttribute
    -0.69
     Waray
    -0.67
    tagext
    -0.66
    AddTagHelper
    -0.63
     estekak
    -0.62
    POSITIVE LOGITS
    ξι
    0.49
     Natuur
    0.48
     Cancer
    0.47
     Of
    0.47
    arakhand
    0.46
    thers
    0.46
    MARKS
    0.45
     Action
    0.45
    ведении
    0.45
    OfType
    0.44
    Activations Density 0.180%

    No Known Activations