© 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. 13-GEMMASCOPE-RES-65K
    6. 16736
    Prev
    Next
    INDEX
    Explanations

    causal relationships in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.52
     Ooster
    -0.50
    indd
    -0.46
     moon
    -0.44
    incl
    -0.44
    Installed
    -0.44
    zdy
    -0.44
    richTextPanel
    -0.43
     danced
    -0.43
    boj
    -0.43
    POSITIVE LOGITS
    étit
    0.70
     kasarigan
    0.68
    ungguhnya
    0.65
    MigrationBuilder
    0.64
    lète
    0.64
    原始内容
    0.63
     '{@
    0.61
    ::::::::
    0.60
    shadowOpacity
    0.59
    ajoz
    0.59
    Activations Density 0.061%

    No Known Activations