© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 26
    Prev
    Next
    INDEX
    Explanations

    terms associated with late-night scenarios or activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the word "late"

    np_acts-logits-general · gemini-2.0-flash

    late time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    #+#
    -0.58
     recién
    -0.57
     vtk
    -0.57
     Marit
    -0.56
    dır
    -0.55
     BioLib
    -0.54
    reu
    -0.52
    ktı
    -0.52
    épendant
    -0.51
    IPAddress
    -0.51
    POSITIVE LOGITS
    comers
    0.86
     lamented
    0.80
    comer
    0.79
     afternoon
    0.78
     night
    0.69
     arrivals
    0.65
    blooming
    0.64
     stages
    0.63
     evening
    0.63
     stage
    0.62
    Activations Density 0.079%

    No Known Activations