© 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. 0-GEMMASCOPE-RES-65K
    6. 10590
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various types of differences or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.60
    ><?
    -0.53
    displayName
    -0.52
    ="<?
    -0.52
    <?
    -0.49
    canestro
    -0.49
    むしろ
    -0.48
    プライズ
    -0.48
    mmä
    -0.47
    DockStyle
    -0.46
    POSITIVE LOGITS
     InputDecoration
    0.95
    HtmlAttribute
    0.77
     Teacher
    0.76
     Sensor
    0.74
     Fara
    0.70
    SizeF
    0.69
     Phal
    0.68
     ricotta
    0.68
     Phar
    0.68
    Ph
    0.68
    Activations Density 0.071%

    No Known Activations