© 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. 15-GEMMASCOPE-RES-16K
    11. 562
    Prev
    Next
    INDEX
    Explanations

    percentages and their context in numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nationaux
    -0.39
     voisins
    -0.34
     consultez
    -0.34
    lloworld
    -0.33
    woners
    -0.33
    ksz
    -0.32
     commerciaux
    -0.31
     poziomie
    -0.31
     Zwecke
    -0.31
    เหตุ
    -0.31
    POSITIVE LOGITS
    
    0.81
    
    0.73
    Personensuche
    0.71
     percent
    0.67
    ValueStyle
    0.66
    TagMode
    0.60
    percent
    0.59
    MathML
    0.59
    󠁿
    0.58
    izr
    0.58
    Activations Density 0.356%

    No Known Activations