© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7632
    Prev
    Next
    INDEX
    Explanations

    present tense time indicators

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

    Beginning of sentence, often after conjunction

    np_acts-logits-general · gemini-2.0-flash

    now, followed by punctuation or conjunction

    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
    Negative Logits
    weakSelf
    -0.42
    Around
    -0.33
    monių
    -0.32
    RemoveAt
    -0.32
     promouvoir
    -0.32
    ../../
    -0.31
     hâte
    -0.30
     houſe
    -0.30
     acús
    -0.29
     nôtre
    -0.29
    POSITIVE LOGITS
     oprot
    0.60
    isContained
    0.59
    vician
    0.58
    +#+#
    0.57
     snippetHide
    0.56
    rrggbb
    0.55
     PeEnEo
    0.55
    arate
    0.55
    hebt
    0.55
     InputDecoration
    0.54
    Activations Density 0.067%

    No Known Activations