© 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. 31-GEMMASCOPE-RES-16K
    11. 9691
    Prev
    Next
    INDEX
    Explanations

    terms related to the festival Lammas and similar variations or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "Lam" (likely detecting "Lammas," a harvest festival, or surnames/terms containing this substring).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.41
     Pura
    -0.41
    andExpect
    -0.39
    RRect
    -0.39
    ftagPool
    -0.38
    styleable
    -0.38
    jsdelivr
    -0.38
     ""],
    -0.36
     primar
    -0.35
    usercontent
    -0.35
    POSITIVE LOGITS
     Lam
    0.71
    Lam
    0.68
     Lem
    0.58
    Tembelea
    0.56
    Lamb
    0.52
    Lem
    0.51
     LAM
    0.50
     Lamp
    0.50
     Lamb
    0.49
     لام
    0.48
    Activations Density 0.146%

    No Known Activations