© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8818
    Prev
    Next
    INDEX
    Explanations

    references to file names, actor names, and data formatting elements in code

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

    Followed by assignment or a colon

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers

    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
    InstanceOf
    -0.52
    aco
    -0.49
    memset
    -0.49
    UserDTO
    -0.48
    di
    -0.47
    hofer
    -0.46
    dej
    -0.45
     meng
    -0.45
    isinstance
    -0.45
    ulka
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.93
     resourceCulture
    0.91
    writeFieldEnd
    0.81
    DoubleQuotes
    0.80
    IBarButtonItem
    0.77
    HasForeignKey
    0.77
     ModelExpression
    0.75
    曖昧さ回避
    0.75
     betweenstory
    0.72
     CreateTagHelper
    0.71
    Activations Density 0.336%

    No Known Activations