© 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. 1877
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific research and molecular biology

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

    "Areas" or "regions" of something

    np_acts-logits-general · gemini-2.0-flash

    areas and regions

    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
    StructEnd
    -0.51
    !*\
    -0.51
    __).
    -0.49
    uskan
    -0.49
    ]^{-
    -0.48
    simpleType
    -0.47
    aarrggbb
    -0.46
    sizeCache
    -0.46
    ynb
    -0.46
     ujednoznacz
    -0.46
    POSITIVE LOGITS
     areas
    2.15
     area
    1.98
    areas
    1.82
     Areas
    1.82
    Areas
    1.69
    area
    1.68
     AREAS
    1.63
     regions
    1.63
    Area
    1.54
     Area
    1.52
    Activations Density 0.926%

    No Known Activations