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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15462
    Prev
    Next
    INDEX
    Explanations

    attributes related to roofing materials and their characteristics

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

    Roofs and roofing elements

    np_acts-logits-general · gemini-2.0-flash

    roof parts and features

    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
    HtmlAttribute
    -0.50
     MonoBehaviour
    -0.50
     Damas
    -0.49
    benzyl
    -0.49
     Cade
    -0.48
    комнат
    -0.47
     Squid
    -0.47
    merce
    -0.47
    inine
    -0.46
     neutron
    -0.46
    POSITIVE LOGITS
     roof
    2.00
     roofs
    1.74
     Roof
    1.73
    Roof
    1.72
     roofing
    1.65
    roof
    1.60
     ROOF
    1.57
     rooftop
    1.48
     Roofing
    1.45
     rooftops
    1.41
    Activations Density 0.087%

    No Known Activations