© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 277
    Prev
    Next
    INDEX
    Explanations

    references to cultural or historical figures involved in literary or social discourse

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

    references to Southern literature and its themes

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

    opposing rejecting critiquing

    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
     kling
    -0.54
    ftagPool
    -0.52
     circonstances
    -0.51
     profesion
    -0.51
     Konink
    -0.51
     sticky
    -0.50
     Storia
    -0.49
     Verfügung
    -0.49
     presently
    -0.49
     elefante
    -0.49
    POSITIVE LOGITS
    opposed
    0.79
     rejection
    0.76
     opposes
    0.74
     opposed
    0.73
     reject
    0.72
    "?>
    0.71
     critique
    0.71
    reject
    0.70
     Reject
    0.70
     oppose
    0.70
    Activations Density 0.110%

    No Known Activations