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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 873
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names

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

    mentions of specific individuals or contributors associated with projects or works

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

    Dre, Drew, Dresden, Dreizin

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     typelib
    -0.61
    awtextra
    -0.57
    fjspx
    -0.56
    BeginContext
    -0.53
    Colm
    -0.53
     transfieras
    -0.53
     StatefulWidget
    -0.53
    ไร
    -0.52
    migiano
    -0.52
     BoxDecoration
    -0.52
    POSITIVE LOGITS
     Dre
    0.86
    Dre
    0.68
    ember
    0.59
     DRE
    0.56
     createSlice
    0.56
    globo
    0.55
     Fantasia
    0.54
    cury
    0.54
     dre
    0.53
    ان
    0.53
    Activations Density 0.018%

    No Known Activations