© 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. 39-GEMMASCOPE-RES-16K
    6. 4993
    Prev
    Next
    INDEX
    Explanations

    details about architectural features and historical context in buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSprite
    -0.46
     فريبيس
    -0.38
    सन्दर्भ
    -0.38
    DataPropertyName
    -0.35
    URLException
    -0.35
     berke
    -0.35
     mounds
    -0.35
     densities
    -0.34
     malin
    -0.34
     filo
    -0.34
    POSITIVE LOGITS
     organ
    0.81
     church
    0.81
     choir
    0.77
     nave
    0.75
     chancel
    0.70
     Nave
    0.67
     igreja
    0.65
     organs
    0.64
     organist
    0.64
     chapels
    0.64
    Activations Density 0.300%

    No Known Activations