© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7248
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric values or structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iocene
    -0.76
    alnız
    -0.60
    akaian
    -0.58
    awtextra
    -0.55
     endregion
    -0.54
    ratto
    -0.54
    Kontrola
    -0.54
     ​​
    -0.52
    discuss
    -0.51
    Geneva
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.77
    bootstrapcdn
    0.76
     ويكيپيديا
    0.61
     kaynağından
    0.57
    ␮
    0.55
    AndEndTag
    0.54
    NamedQueries
    0.54
    jeen
    0.54
    TypedDataSet
    0.53
    Jeografia
    0.51
    Activations Density 0.600%

    No Known Activations