© 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. 7-GEMMASCOPE-RES-16K
    6. 14937
    Prev
    Next
    INDEX
    Explanations

    references to periods of time, specifically years and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obligé
    -0.39
     drewna
    -0.35
     gouvern
    -0.35
     transparencia
    -0.35
     operações
    -0.34
     utford
    -0.34
     caráter
    -0.34
     territorios
    -0.34
     chaves
    -0.34
    atteindre
    -0.34
    POSITIVE LOGITS
     спустя
    0.63
    oa̍t
    0.56
     MONTHS
    0.54
     prior
    0.53
    protoimpl
    0.53
     Months
    0.52
    httphttps
    0.52
     minutes
    0.50
    isContained
    0.50
     PRIOR
    0.50
    Activations Density 0.291%

    No Known Activations