© 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. 7705
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming, technology, and digital processes

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

    followed by conjunctions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    so that

    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
     deſſen
    -0.65
    rungsseite
    -0.65
     dieſes
    -0.63
     >=",
    -0.62
    onedDateTime
    -0.61
    enderror
    -0.61
    PreferredItem
    -0.61
     unſer
    -0.60
     AppCompatTheme
    -0.60
    ſammen
    -0.60
    POSITIVE LOGITS
     so
    1.79
     zodat
    1.53
     affinch
    1.10
    以便
    1.08
     supaya
    1.05
     sehingga
    1.02
     så
    1.02
     כך
    0.96
    so
    0.92
     così
    0.92
    Activations Density 1.076%

    No Known Activations