© 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 EvalsExportsinterp-engineNEWAPI 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. 6336
    Prev
    Next
    INDEX
    Explanations

    instances of common syntactic patterns and phrases in various languages

    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
     dieux
    -0.51
     sobě
    -0.47
     fundido
    -0.47
     journaux
    -0.46
     världen
    -0.45
     trasero
    -0.44
     informática
    -0.44
     Bélgica
    -0.44
     նաև
    -0.44
     movilidad
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.60
     يتيمه
    0.55
    tagHelperRunner
    0.54
     surla
    0.53
    quela
    0.53
    +#+
    0.52
    QMetaType
    0.52
     CURLOPT
    0.52
     للمعارف
    0.52
    :+:
    0.51
    Activations Density 0.064%

    No Known Activations