© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 589
    Prev
    Next
    INDEX
    Explanations

    references to academic manuscripts and associated elements

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

    sections related to funding and support acknowledgments in research papers

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

    supported in part by

    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
    Initializable
    -0.52
    Хи
    -0.50
     Wikidata
    -0.48
    #![
    -0.47
    nals
    -0.47
    DotNetBar
    -0.47
    principalTable
    -0.46
     ύ
    -0.44
    арак
    -0.44
    marvin
    -0.44
    POSITIVE LOGITS
    SBATCH
    0.69
     CURLOPT
    0.68
    ftagPool
    0.64
     createSlice
    0.61
    nocache
    0.61
     BoxDecoration
    0.58
    MemoryWarning
    0.57
    TargetException
    0.56
    rizona
    0.56
     FontFamily
    0.56
    Activations Density 0.002%

    No Known Activations