© 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. 38-GEMMASCOPE-RES-16K
    11. 13502
    Prev
    Next
    INDEX
    Explanations

    references to specific architectural structures or buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.38
    レージ
    -0.35
     muebles
    -0.35
     kasarigan
    -0.34
     propOrder
    -0.34
     kautta
    -0.33
    enderror
    -0.33
     pelatih
    -0.33
    Coach
    -0.32
    errHandler
    -0.32
    POSITIVE LOGITS
     tower
    2.11
     towers
    1.98
    tower
    1.77
     Tower
    1.76
    Tower
    1.69
     TOWER
    1.59
    towers
    1.51
     Towers
    1.49
     tallest
    1.48
     towering
    1.40
    Activations Density 0.347%

    No Known Activations