© 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. 25-GEMMASCOPE-RES-16K
    11. 10718
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to BitTorrent and file sharing technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.63
     secondaires
    -0.57
     transfieras
    -0.56
     disambiguazione
    -0.54
    Życiorys
    -0.52
    AndroidJUnit
    -0.51
    enser
    -0.49
    <tfoot>
    -0.49
    __(/*!
    -0.49
    CodeAttribute
    -0.48
    POSITIVE LOGITS
    meal
    0.86
    ########.
    0.82
    terness
    0.71
    wise
    0.70
    chy
    0.65
    WISE
    0.61
    moji
    0.61
    jointe
    0.57
    ching
    0.57
    -------------</
    0.56
    Activations Density 0.240%

    No Known Activations