© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8469
    Prev
    Next
    INDEX
    Explanations

    references to legal matters and personal experiences related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⎣
    -0.43
     purpoſe
    -0.42
     مرئيه
    -0.42
    MessageOf
    -0.37
    synthesize
    -0.37
    xions
    -0.37
    ikyuu
    -0.37
    ագրություններ
    -0.36
    úsqueda
    -0.35
    siasi
    -0.35
    POSITIVE LOGITS
     heard
    2.16
     hear
    2.00
     hearing
    1.97
     hears
    1.96
    heard
    1.66
     Hearing
    1.61
    hearing
    1.60
    Hearing
    1.55
    hear
    1.52
     Hear
    1.48
    Activations Density 0.501%

    No Known Activations