© 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. 2857
    Prev
    Next
    INDEX
    Explanations

    information about individuals, specifically their professions, achievements, and biographical details

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

    "[Name] is best/known as"

    np_acts-logits-general · gemini-2.0-flash

    best known for

    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
    AndEndTag
    -0.77
    บัติ
    -0.57
    yntaxException
    -0.54
    łec
    -0.49
     olisi
    -0.46
    ngdoc
    -0.46
    ximate
    -0.45
    Geographie
    -0.44
     preventiva
    -0.44
    urgy
    -0.44
    POSITIVE LOGITS
     known
    1.81
     best
    1.77
     famous
    1.62
     Known
    1.57
    known
    1.57
    Known
    1.55
    best
    1.49
    famous
    1.45
     KNOWN
    1.40
     famed
    1.39
    Activations Density 0.256%

    No Known Activations