© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7883
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or duration

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

    duration of time

    np_acts-logits-general · gemini-2.0-flash

    time elapsed before event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.76
     ſta
    -0.69
     ſch
    -0.68
    [@BOS@]
    -0.66
    <unused80>
    -0.66
    <unused16>
    -0.66
    <unused74>
    -0.66
    <unused52>
    -0.66
    <unused3>
    -0.66
    <unused8>
    -0.66
    POSITIVE LOGITS
     until
    0.63
     between
    0.54
     till
    0.54
    until
    0.54
     since
    0.44
     Until
    0.41
    Until
    0.41
     before
    0.40
     até
    0.40
     for
    0.39
    Activations Density 0.170%

    No Known Activations