© 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. 11704
    Prev
    Next
    INDEX
    Explanations

    references to institutional affiliations and funding sources in research papers

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

    Academic or research-related terms

    np_acts-logits-general · gemini-2.0-flash

    research institutions and organizations

    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
    ########.
    -0.63
    Abp
    -0.60
     становника
    -0.57
    MLE
    -0.56
    UBS
    -0.54
     AssemblyVersion
    -0.54
     FetchType
    -0.53
    FileVersion
    -0.50
    EDEFAULT
    -0.49
    AMIENTO
    -0.49
    POSITIVE LOGITS
     research
    0.95
     project
    0.83
     Research
    0.83
    research
    0.81
     consortium
    0.78
     Center
    0.76
     Centre
    0.76
    Research
    0.75
    tagHelperRunner
    0.71
    project
    0.71
    Activations Density 0.425%

    No Known Activations