© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11819
    Prev
    Next
    INDEX
    Explanations

    terms related to roofing materials and their properties

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

    Building exteriors and roofing

    np_acts-logits-general · gemini-2.0-flash

    buildings, rooftops, and exteriors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     salles
    -0.42
     meja
    -0.40
     encaje
    -0.31
     conter
    -0.31
     createSlice
    -0.30
     talent
    -0.30
    getSupport
    -0.29
    テーブル
    -0.29
     enseignants
    -0.29
     ruang
    -0.29
    POSITIVE LOGITS
     Exterior
    0.89
    exterior
    0.84
     exterior
    0.79
    Exterior
    0.77
     roofing
    0.76
    roof
    0.72
    Roof
    0.72
     roof
    0.71
     Roofing
    0.71
     Roof
    0.68
    Activations Density 0.347%

    No Known Activations