© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9092
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or categories, particularly "P" followed by a number or term related to structured data

    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
     تضيفلها
    -0.35
     Biôgrafia
    -0.32
    ervlak
    -0.30
    Jîn
    -0.30
    继
    -0.28
    XmlAccessType
    -0.27
    readyState
    -0.27
     Horizon
    -0.27
    principalTable
    -0.27
    dingen
    -0.26
    POSITIVE LOGITS
    mybatisplus
    0.70
     Plu
    0.57
    pump
    0.56
    sequelize
    0.56
     Perci
    0.56
     pumped
    0.55
    PointerException
    0.55
    Plu
    0.54
    Poor
    0.54
    Preferences
    0.54
    Activations Density 0.666%

    No Known Activations