© 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. 13-GEMMASCOPE-RES-16K
    11. 6213
    Prev
    Next
    INDEX
    Explanations

    terms related to health-related substances and entities

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

    formal or technical nouns, particularly those referring to abstract concepts, objects, or categories in specialized or technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @georglange4
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.97
     متعلقه
    -0.96
    AccessorTable
    -0.94
    makeConstraints
    -0.90
    parsedMessage
    -0.89
    脚注の使い方
    -0.86
     beginnetje
    -0.85
     дописавши
    -0.85
    StoryboardSegue
    -0.84
     referenties
    -0.84
    POSITIVE LOGITS
     for
    0.65
     that
    0.65
     to
    0.60
     of
    0.53
     in
    0.53
     whose
    0.52
     we
    0.51
     worth
    0.50
     with
    0.49
    kota
    0.49
    Activations Density 0.448%

    No Known Activations