© 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. 7457
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating recommendations or obligations

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

    "should" or a misspelling

    np_acts-logits-general · gemini-2.0-flash

    should be

    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
    CPtr
    -0.46
     Rine
    -0.44
    itatis
    -0.42
    existsSync
    -0.41
     VIAF
    -0.39
    execSQL
    -0.38
     ​​
    -0.37
    󠁧
    -0.37
     CascadeType
    -0.37
    ️
    -0.37
    POSITIVE LOGITS
    should
    0.74
    Should
    0.67
    ered
    0.66
     Should
    0.64
    chieht
    0.59
     SHOULD
    0.57
    hould
    0.57
     saites
    0.55
     should
    0.55
     feroit
    0.55
    Activations Density 0.124%

    No Known Activations