© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 757
    Prev
    Next
    INDEX
    Explanations

    references to academic programs or institutions

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

    terms related to academic research or scholarship

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

    academic contexts

    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
     виправивши
    -0.87
    webElementXpaths
    -0.82
    rungsseite
    -0.76
    AddTagHelper
    -0.74
     المعيارى
    -0.72
     resourceCulture
    -0.72
    BufferException
    -0.72
    $_['
    -0.72
     surla
    -0.71
    #+#
    -0.71
    POSITIVE LOGITS
    ians
    0.99
    ian
    0.83
     pursuits
    0.63
     houſe
    0.62
     parlant
    0.58
    ership
    0.56
    IAN
    0.56
     faſt
    0.55
     Houſe
    0.55
    ally
    0.54
    Activations Density 0.007%

    No Known Activations