© 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. 8628
    Prev
    Next
    INDEX
    Explanations

    references to popular television shows and their portrayal of relationships

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

    Quotation marks

    np_acts-logits-general · gemini-2.0-flash

    TV show titles

    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
     film
    -0.53
     Inhalts
    -0.50
    ForRow
    -0.48
     movie
    -0.47
    filme
    -0.45
    ("${
    -0.45
     Adkins
    -0.44
    astéro
    -0.44
    ItemBackground
    -0.44
     Regie
    -0.43
    POSITIVE LOGITS
    igshid
    0.63
    脚注の使い方
    0.62
     חיצוניים
    0.58
    queryInterface
    0.57
    ScopeManager
    0.57
    $__
    0.56
    principalTable
    0.55
     Efq
    0.54
     semarang
    0.53
    THISDAY
    0.53
    Activations Density 0.103%

    No Known Activations