© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14596
    Prev
    Next
    INDEX
    Explanations

    references to leaves and related plant structures

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

    "leaf" followed by a symptom or disease

    np_acts-logits-general · gemini-2.0-flash

    leaf and flower parts

    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
     HasFactory
    -0.96
    rungsseite
    -0.73
    --)
    
    -0.73
     numberWith
    -0.67
    DotNetBar
    -0.67
    setVerticalGroup
    -0.66
     createSlice
    -0.66
    onedDateTime
    -0.64
    <?>>
    -0.63
    SourceChecksum
    -0.63
    POSITIVE LOGITS
    adpleegd
    0.57
     sprigs
    0.55
    Xna
    0.54
     petals
    0.51
     gré
    0.51
     aérienne
    0.51
    ArgsConstructor
    0.49
     twig
    0.48
    ьаж
    0.47
    Vase
    0.47
    Activations Density 0.121%

    No Known Activations