© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 9043
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "toggle" and terms related to bans 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.78
    VIAF
    -0.73
    webElementGuid
    -0.60
     consultato
    -0.58
    prising
    -0.58
     secret
    -0.57
    rets
    -0.56
    assins
    -0.54
    tür
    -0.54
    Nonnull
    -0.54
    POSITIVE LOGITS
    toggle
    0.90
    Toggle
    0.88
     Invo
    0.75
     Invoice
    0.74
    Invoice
    0.73
     Toggle
    0.72
     invoice
    0.72
     unfavourable
    0.68
    Imo
    0.68
    (!
    0.67
    Activations Density 0.043%

    No Known Activations