© 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. 7-GEMMASCOPE-RES-16K
    11. 14306
    Prev
    Next
    INDEX
    Explanations

    the term "general" or variations of it used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tirol
    -0.76
     precisamente
    -0.71
    servez
    -0.71
     Adkins
    -0.69
    wußt
    -0.69
    werkt
    -0.64
     végétale
    -0.63
    kå
    -0.63
     spermato
    -0.63
     Mussolini
    -0.63
    POSITIVE LOGITS
     general
    1.73
    general
    1.67
    GENERAL
    1.64
     General
    1.63
    General
    1.61
     GENERAL
    1.57
    eneral
    1.54
     generale
    1.43
     generales
    1.28
     allgemeine
    1.27
    Activations Density 0.121%

    No Known Activations