© 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. 12-GEMMASCOPE-RES-16K
    11. 282
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and claims related to purchases

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

    language indicating solicitations or scams (offers/requests involving awards, prizes, fees, payments, account activation, or similar financial enticements).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.69
    :✨
    -0.60
    NUMX
    -0.58
    KommentareTeilen
    -0.58
     lenker
    -0.57
     onBind
    -0.54
    styleType
    -0.51
    المناصب
    -0.51
     ?>>
    -0.51
     halo
    -0.51
    POSITIVE LOGITS
     credere
    0.53
    NewUrlParser
    0.53
    ścio
    0.47
     urgente
    0.47
    ceğini
    0.47
     confidential
    0.47
     Caj
    0.47
     opér
    0.46
    lemen
    0.46
     Trans
    0.45
    Activations Density 0.141%

    No Known Activations