© 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. 18-GEMMASCOPE-RES-16K
    11. 4167
    Prev
    Next
    INDEX
    Explanations

    questions about programming concepts in JavaScript

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

    Followed by connecting words in Spanish, Portuguese, or French

    np_acts-logits-general · gemini-2.0-flash

    conjunctions connecting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.81
     volna
    -0.70
    Assista
    -0.62
     aient
    -0.60
    Parabéns
    -0.59
    proper
    -0.59
     Comunicação
    -0.57
     proper
    -0.56
     Coloque
    -0.55
     Vgl
    -0.55
    POSITIVE LOGITS
    出版年
    0.65
     can
    0.61
     do
    0.58
     mergeFrom
    0.58
    //
    0.56
    onOptions
    0.55
     EconPapers
    0.54
    حياتها
    0.54
     have
    0.53
    RenderAtEndOf
    0.53
    Activations Density 0.035%

    No Known Activations