© 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. 28-GEMMASCOPE-RES-16K
    11. 7534
    Prev
    Next
    INDEX
    Explanations

    instances of character names and their actions in narratives

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

    Word preceding past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    events unfolding sequentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.39
     moyen
    -0.34
    scaleX
    -0.34
    critical
    -0.34
     bast
    -0.33
     bornes
    -0.33
    drawing
    -0.33
     „
    -0.33
    XDECREF
    -0.32
    Fountain
    -0.32
    POSITIVE LOGITS
     then
    0.90
     entonces
    0.82
     thereupon
    0.81
     eventually
    0.76
     então
    0.75
     continued
    0.75
     następnie
    0.75
     subsequently
    0.72
     سپس
    0.71
     vervolgens
    0.69
    Activations Density 0.520%

    No Known Activations