© 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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6767
    Prev
    Next
    INDEX
    Explanations

    instances of "gap," "gaps," and "hole" reflecting missing information or deficiencies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
    addLast
    -0.30
     setShow
    -0.29
    setDisplay
    -0.28
     adults
    -0.28
    asString
    -0.28
    zną
    -0.28
     Duro
    -0.27
    dispatch
    -0.27
    ToServer
    -0.27
     erhoben
    -0.27
    POSITIVE LOGITS
     gaps
    1.70
     gap
    1.66
     Gaps
    1.61
     holes
    1.54
    Gap
    1.52
    gaps
    1.52
     Gap
    1.51
     hole
    1.48
    gap
    1.45
     HOLE
    1.40
    Activations Density 0.417%

    No Known Activations