© 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. 3-GEMMASCOPE-RES-16K
    11. 9084
    Prev
    Next
    INDEX
    Explanations

    phrases indicating usefulness or suitability for particular purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibatis
    -0.49
    رشف
    -0.48
    acterium
    -0.47
    GeoNames
    -0.46
     препратки
    -0.46
    бурга
    -0.43
    yscy
    -0.41
    AsUp
    -0.41
    (__('
    -0.41
     prema
    -0.41
    POSITIVE LOGITS
    useful
    0.79
     Useful
    0.76
     useful
    0.71
    RECOMMENDED
    0.70
     útil
    0.69
    enumii
    0.67
    Useful
    0.67
     Prata
    0.62
    适用于
    0.62
    Portale
    0.61
    Activations Density 0.324%

    No Known Activations