© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8415
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the passage of time or duration

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

    Time passing; duration

    np_acts-logits-general · gemini-2.0-flash

    time since or before

    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
     kasarigan
    -0.49
     متعلقه
    -0.49
    исленность
    -0.47
     EconPapers
    -0.47
    ChildScrollView
    -0.47
     createSprite
    -0.45
    Gla
    -0.44
    ⤹
    -0.41
    bited
    -0.41
    PYX
    -0.41
    POSITIVE LOGITS
     until
    0.69
     before
    0.65
     between
    0.64
     Until
    0.59
     till
    0.57
    until
    0.56
    Until
    0.55
     bevor
    0.50
    before
    0.50
     voordat
    0.50
    Activations Density 0.203%

    No Known Activations