© 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. 14-GEMMASCOPE-RES-16K
    6. 8312
    Prev
    Next
    INDEX
    Explanations

    numerical or special characters in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.90
    fromnode
    -0.69
    Personensuche
    -0.66
    featureID
    -0.63
    hyrchwyd
    -0.61
     Italijanski
    -0.59
     kasarigan
    -0.59
    atcher
    -0.59
     jsPsych
    -0.58
     PagesJaunes
    -0.58
    POSITIVE LOGITS
    AddTagHelper
    0.42
     تانيه
    0.40
    jména
    0.35
    imageshack
    0.33
     sentidos
    0.33
     soutien
    0.33
     şeyi
    0.32
     Administración
    0.30
     daarvan
    0.30
     épreuves
    0.29
    Activations Density 0.914%

    No Known Activations