© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4151
    Prev
    Next
    INDEX
    Explanations

    references to business and operational improvements in restaurants

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

    businesses, brands, and franchises

    np_acts-logits-general · gemini-2.0-flash

    franchises and chains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     producteur
    -0.56
    hoedd
    -0.55
     disambiguazione
    -0.54
     Familienname
    -0.52
    .*")]
    -0.51
    дельник
    -0.51
    KURZBESCHREIBUNG
    -0.49
    yntaxException
    -0.49
    ➟
    -0.48
    QualifiedName
    -0.48
    POSITIVE LOGITS
     franchise
    1.59
     franch
    1.39
     Franchise
    1.36
    Franchise
    1.34
     franchi
    1.32
     franchises
    1.29
    franchise
    1.29
     chain
    1.21
    franch
    1.17
     chains
    1.17
    Activations Density 0.154%

    No Known Activations