Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3113
    Prev
    Next
    INDEX
    Explanations

    descriptions of building materials and their characteristics

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

    roofs and roofing

    np_acts-logits-general · gemini-2.0-flash

    roof and roofing materials

    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
     Cade
    -0.57
     cavitation
    -0.50
     TableColumn
    -0.49
    JspWriter
    -0.47
     décret
    -0.47
     Dig
    -0.46
    benzyl
    -0.46
     glycer
    -0.46
    plasma
    -0.45
    Reagent
    -0.45
    POSITIVE LOGITS
     roof
    1.99
     roofs
    1.82
    Roof
    1.70
     Roof
    1.69
    roof
    1.67
     roofing
    1.60
     ROOF
    1.59
     rooftops
    1.43
     rooftop
    1.42
     Roofing
    1.39
    Activations Density 0.067%

    No Known Activations