© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7828
    Prev
    Next
    INDEX
    Explanations

    references to indirect involvement and media's role in communication

    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
    AddTagHelper
    -0.67
     manuten
    -0.41
     postIndex
    -0.41
    Encyklopedia
    -0.39
     wikipagina
    -0.39
    ciorys
    -0.38
    (!__
    -0.38
    ✷
    -0.38
    ñores
    -0.37
     búsquedas
    -0.37
    POSITIVE LOGITS
     vehicle
    1.61
     vehicles
    1.52
     channels
    1.36
     Vehicles
    1.30
    vehicle
    1.30
     mechanism
    1.27
     channel
    1.26
     medium
    1.25
     vehículo
    1.25
     veículo
    1.24
    Activations Density 0.652%

    No Known Activations