© 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 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. 9116
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities along with their relationships or affiliations

    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
    IsContent
    -0.84
     Biôgrafia
    -0.82
    protoimpl
    -0.81
     <<<<<<<<<<<<<<
    -0.79
    +#+#
    -0.76
    nonatomic
    -0.74
    ----</
    -0.73
    səhifə
    -0.71
     nonatomic
    -0.70
     snippetHide
    -0.70
    POSITIVE LOGITS
     Siglo
    0.37
     préférences
    0.35
     Constitucional
    0.34
    InternalFrame
    0.33
     fact
    0.33
     configurer
    0.32
     MacArthur
    0.31
     espect
    0.30
     frecuencia
    0.30
    Callable
    0.30
    Activations Density 1.512%

    No Known Activations