© 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. 31-GEMMASCOPE-RES-16K
    11. 3311
    Prev
    Next
    INDEX
    Explanations

    references to news broadcasts and reporting formats

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

    specific time durations and temporal measurements (hours, minutes, seconds).

    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
     week
    -0.66
     Days
    -0.64
    Days
    -0.62
     yearly
    -0.62
    Week
    -0.62
     days
    -0.61
    Weeks
    -0.60
     Week
    -0.59
     year
    -0.58
     weeks
    -0.58
    POSITIVE LOGITS
     hour
    1.82
     HOUR
    1.57
     Hour
    1.55
    hour
    1.53
    Hour
    1.46
     hours
    1.45
     hourly
    1.41
     minutes
    1.29
     Stunde
    1.29
    hours
    1.24
    Activations Density 0.875%

    No Known Activations