© 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. 41-GEMMASCOPE-RES-16K
    6. 7759
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific jargon related to software and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ation
    -0.87
     tion
    -0.79
    ATION
    -0.79
    ERATION
    -0.76
    tition
    -0.75
    titution
    -0.72
     contraction
    -0.72
     ation
    -0.71
    lation
    -0.71
    ition
    -0.71
    POSITIVE LOGITS
     cheminée
    0.61
    expandindo
    0.60
     ब्रेकडाउन
    0.57
    enumii
    0.57
     betweenstory
    0.57
    AndroidJUnit
    0.53
     sagesse
    0.52
     ong
    0.52
    AndEndTag
    0.50
     bière
    0.50
    Activations Density 0.304%

    No Known Activations