© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8376
    Prev
    Next
    INDEX
    Explanations

    keywords associated with auditing and performance evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.59
     nahilalakip
    -0.44
    assertNotNull
    -0.40
     للمعارف
    -0.38
    การ
    -0.37
     proposito
    -0.36
     فريبيس
    -0.35
    IsOptional
    -0.35
    ApiModel
    -0.35
    بوع
    -0.35
    POSITIVE LOGITS
    parsedMessage
    0.71
    featureID
    0.69
    multer
    0.54
    oa̍t
    0.52
    AnchorTagHelper
    0.51
     fieldNum
    0.49
     Football
    0.47
    able
    0.47
    postsleuth
    0.47
    SharedDtor
    0.47
    Activations Density 0.874%

    No Known Activations