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. 3-GEMMASCOPE-RES-16K
    6. 12425
    Prev
    Next
    INDEX
    Explanations

    terms and references related to roofs and roofing materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.72
    onActivityResult
    -0.70
    JspWriter
    -0.69
    Reagent
    -0.68
    enumii
    -0.68
     Chatterjee
    -0.67
    rlrl
    -0.67
    errHandler
    -0.67
    ISI
    -0.65
    ariato
    -0.65
    POSITIVE LOGITS
     roof
    3.28
     Roof
    2.92
     roofs
    2.77
    roof
    2.76
     ROOF
    2.73
    Roof
    2.69
     rooftops
    2.03
     rooftop
    2.03
     roofing
    2.00
     toit
    1.71
    Activations Density 0.064%

    No Known Activations