© 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. 22-GEMMASCOPE-RES-16K
    6. 14349
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal agreements and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.41
     recargable
    -0.40
     provisoire
    -0.35
    IContainer
    -0.35
     nuage
    -0.35
     perfección
    -0.35
     civilización
    -0.35
     cejas
    -0.34
     getItemCount
    -0.34
     humanidade
    -0.34
    POSITIVE LOGITS
    oa̍t
    0.55
     approval
    0.54
    ymce
    0.50
     approvals
    0.49
     consens
    0.49
     Approval
    0.49
     consult
    0.49
     consent
    0.48
     permission
    0.47
     '\\;'
    0.47
    Activations Density 0.540%

    No Known Activations