© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1063
    Prev
    Next
    INDEX
    Explanations

    statistical metrics related to player performance in baseball

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

    Text before numbers or letters

    np_acts-logits-general · gemini-2.0-flash

    in numbers or names

    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
    sidemargin
    -0.71
    EDEFAULT
    -0.68
    脚注の使い方
    -0.63
    braio
    -0.59
    UnusedPrivate
    -0.59
    cagon
    -0.52
     betweenstory
    -0.52
    XDECREF
    -0.52
    YLON
    -0.51
    istisches
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.60
    ValueStyle
    0.58
     crédit
    0.57
    paravant
    0.55
    SourceChecksum
    0.54
    neté
    0.52
    XmlAccessorType
    0.50
     mound
    0.50
     credit
    0.50
    LayoutPanel
    0.50
    Activations Density 0.116%

    No Known Activations