© 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 - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2934
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions, specifically the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {}'.
    -0.61
    GHIJKLM
    -0.61
     \"%
    -0.59
    ^(@)
    -0.57
    ulongan
    -0.54
     getPost
    -0.54
    xffffff
    -0.53
    addContainerGap
    -0.52
     Huntington
    -0.52
     Eigen
    -0.52
    POSITIVE LOGITS
    Và
    0.82
    帖最后由
    0.74
     оригіналу
    0.71
     And
    0.66
    And
    0.66
    mbols
    0.65
    SourceChecksum
    0.65
    IBOutlet
    0.64
    ContentAsync
    0.61
    rativa
    0.61
    Activations Density 0.479%

    No Known Activations