© 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. 15833
    Prev
    Next
    INDEX
    Explanations

    phrases that express connections or relationships between multiple elements

    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
    ̈́
    -0.50
     they
    -0.48
     للمعارف
    -0.44
     she
    -0.44
     jadx
    -0.44
    Koordinaten
    -0.43
    Erstellt
    -0.42
     horizontally
    -0.40
    EndContext
    -0.40
     BOTH
    -0.39
    POSITIVE LOGITS
     its
    0.87
     how
    0.85
     cómo
    0.75
     bagaimana
    0.74
     their
    0.72
     whether
    0.65
    aimana
    0.63
     její
    0.62
     związane
    0.61
     jego
    0.61
    Activations Density 0.698%

    No Known Activations