© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5984
    Prev
    Next
    INDEX
    Explanations

    terms related to education and student integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chi̍t
    -0.69
     بيها
    -0.60
    MigrationBuilder
    -0.56
    Personendaten
    -0.55
    zuli
    -0.55
    oustics
    -0.55
     kasarigan
    -0.54
     Grecs
    -0.52
     jälkeen
    -0.50
    MessageOf
    -0.50
    POSITIVE LOGITS
    %");
    0.73
     Enquanto
    0.66
    stuhl
    0.62
     prepares
    0.61
    مصادر
    0.61
    ictured
    0.59
     Mientras
    0.58
    chränk
    0.57
    wijl
    0.56
    WEBPACK
    0.55
    Activations Density 0.186%

    No Known Activations