© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15319
    Prev
    Next
    INDEX
    Explanations

    instances of negation in a text

    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
    :✨
    -0.77
    +#+#
    -0.73
    oredCriteria
    -0.68
     pinulongan
    -0.65
     CanadaChoose
    -0.63
    Portale
    -0.62
    EndGlobalSection
    -0.60
     Italijanski
    -0.60
    ----</
    -0.60
    Дереккөздер
    -0.60
    POSITIVE LOGITS
     Waray
    0.36
    spesies
    0.32
     density
    0.29
     Seuss
    0.29
    woordig
    0.29
    cześ
    0.28
    Cartney
    0.27
    jillo
    0.27
     prévenir
    0.27
    density
    0.26
    Activations Density 2.329%

    No Known Activations