© 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. 0-GEMMASCOPE-RES-16K
    11. 8166
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sat" and its variations, along with references to saturation levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     importado
    -0.57
     asuntos
    -0.54
     compromisos
    -0.54
     cromado
    -0.50
     instituição
    -0.49
     perdana
    -0.49
     préstamo
    -0.48
     peligroso
    -0.48
     Genehmigung
    -0.48
     kemajuan
    -0.48
    POSITIVE LOGITS
     Sat
    1.72
    Sat
    1.71
     sat
    1.55
    sat
    1.50
     SAT
    1.46
    SAT
    1.43
     saturation
    1.32
     Saturation
    1.25
     saturated
    1.19
     Satur
    1.12
    Activations Density 0.179%

    No Known Activations