© 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. 8150
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to the appeals process

    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
    quium
    -0.45
     obligación
    -0.43
     shutting
    -0.41
     Sheehan
    -0.39
     requerido
    -0.39
    footnotesize
    -0.38
     hypoch
    -0.38
    olsom
    -0.38
     afges
    -0.38
     Kecil
    -0.38
    POSITIVE LOGITS
    Appeal
    1.01
     Appeal
    1.00
     appeal
    0.96
     appeals
    0.95
     appealed
    0.93
    appeal
    0.90
     APPEAL
    0.87
     Appeals
    0.86
    Appe
    0.86
     appealing
    0.73
    Activations Density 1.846%

    No Known Activations