© 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 EvalsExportsinterp-engineNEWAPI 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. 16043
    Prev
    Next
    INDEX
    Explanations

    structures indicating an argument or viewpoint

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

    preceding a type or kind

    np_acts-logits-general · gemini-2.0-flash

    Respiratory syncytial

    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
    AndEndTag
    -0.94
    
    -0.88
    AnchorStyles
    -0.81
    AutoresizingMask
    -0.81
    TagMode
    -0.74
    Демографія
    -0.74
    évaluateur
    -0.73
    بوابة
    -0.72
     ModelExpression
    -0.72
     Numerade
    -0.72
    POSITIVE LOGITS
     ones
    1.17
     celle
    0.87
    jenigen
    0.75
     Celui
    0.73
     celui
    0.72
    のもの
    0.72
    jenige
    0.70
    なもの
    0.69
    ものである
    0.67
     celles
    0.65
    Activations Density 0.832%

    No Known Activations