© 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. 40-GEMMASCOPE-RES-16K
    6. 890
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Juju" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorizaciones
    -0.52
     StatelessWidget
    -0.47
     jPanel
    -0.42
     scom
    -0.42
    ponses
    -0.41
     Publicar
    -0.41
     indisponible
    -0.41
    CrossRef
    -0.41
    ApiProperty
    -0.40
     utafitiHapana
    -0.40
    POSITIVE LOGITS
    Diweddarwch
    0.44
     estekak
    0.40
    parsedMessage
    0.38
    InteropServices
    0.35
    HomeAsUpEnabled
    0.34
    jub
    0.34
    jutsu
    0.33
    kebox
    0.33
    
    0.32
    Ju
    0.32
    Activations Density 0.307%

    No Known Activations