© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 8544
    Prev
    Next
    INDEX
    Explanations

    content related to warnings about graphic or sensitive themes, particularly regarding sexual relationships and violence

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

    fanfiction or chapters

    np_acts-logits-general · gemini-2.0-flash

    author written chapter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    caria
    -0.41
    aryn
    -0.40
    LOV
    -0.38
    uskas
    -0.38
    IDENTITY
    -0.37
    Гля
    -0.37
    +:+
    -0.36
    PRNewswire
    -0.36
    ämpfung
    -0.36
    новништво
    -0.36
    POSITIVE LOGITS
     fanfiction
    1.10
     fanfic
    1.09
     chapter
    0.94
     chapters
    0.91
     fic
    0.89
     Chapter
    0.84
    fanfic
    0.83
     author
    0.82
    chapter
    0.80
     fiction
    0.79
    Activations Density 0.115%

    No Known Activations