Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9637
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to biology and medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.54
    standes
    -0.51
     keterampilan
    -0.48
     \|
    -0.47
    =}
    -0.47
    deauna
    -0.46
     riqueza
    -0.45
    ftagPool
    -0.45
     тест
    -0.44
    IDENTAL
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.94
    BagConstraints
    0.76
    BuildContext
    0.74
    migrationBuilder
    0.72
     butterknife
    0.70
    ConstraintMaker
    0.69
    cor
    0.69
    hint
    0.68
    AutoScale
    0.68
    Corn
    0.68
    Activations Density 2.041%

    No Known Activations