Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6566
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "save."

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     surla
    -0.65
    leiding
    -0.50
    WebControls
    -0.48
     jPanel
    -0.46
    icke
    -0.46
    reys
    -0.45
     Daniel
    -0.44
     Xamarin
    -0.43
    Зноскі
    -0.43
    Descripción
    -0.42
    POSITIVE LOGITS
     save
    4.34
     saving
    4.30
     saves
    4.17
     saved
    4.13
     Save
    3.94
     Saving
    3.83
    Save
    3.79
    save
    3.77
    Saving
    3.60
     Saves
    3.58
    Activations Density 0.046%

    No Known Activations