© 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. 12101
    Prev
    Next
    INDEX
    Explanations

    references to late-night talk shows and their hosts

    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
    MLLoader
    -0.66
     Reſ
    -0.62
     CreateTagHelper
    -0.59
     تضيفلها
    -0.55
    iastical
    -0.55
    TypedDataSet
    -0.54
    ########.
    -0.54
    Parcelize
    -0.53
     nakalista
    -0.53
    PointerException
    -0.53
    POSITIVE LOGITS
    ckså
    0.39
     host
    0.39
    Host
    0.37
    host
    0.36
    Шо
    0.34
     оригіналу
    0.34
     Kimmel
    0.32
    RenderAtEndOf
    0.32
     Host
    0.31
     interviewing
    0.31
    Activations Density 0.340%

    No Known Activations