Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5450
    Prev
    Next
    INDEX
    Explanations

    references to past experiences and activities related to outdoor adventures

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

    Referring back to a place or thing

    np_acts-logits-general · gemini-2.0-flash

    repeat or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.81
     EconPapers
    -0.79
     informée
    -0.77
     MenuView
    -0.73
     ब्रेकडाउन
    -0.72
    RenderAtEndOf
    -0.71
     queſto
    -0.71
    :✨
    -0.68
     Савезне
    -0.68
    oa̍t
    -0.67
    POSITIVE LOGITS
     repeat
    0.75
     repeated
    0.61
    repeat
    0.60
     revisit
    0.58
     visit
    0.57
     wiederhol
    0.54
     revisited
    0.53
    Repeat
    0.51
    ครั้ง
    0.50
    回目
    0.48
    Activations Density 0.415%

    No Known Activations