© 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. 22-GEMMASCOPE-RES-16K
    11. 3203
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between various concepts or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.54
     newBuilder
    -0.45
    WG
    -0.44
     dä
    -0.44
    rowser
    -0.44
     WG
    -0.44
    Predecesor
    -0.43
    Stayed
    -0.43
     Tcp
    -0.43
     Tit
    -0.43
    POSITIVE LOGITS
    ChrTalk
    0.44
     ↓,
    0.41
     esboço
    0.40
     ModelExpression
    0.40
    ]")]
    0.39
    ätigkeit
    0.38
    arschu
    0.38
    ьаж
    0.37
    writeFieldEnd
    0.37
    .*")]
    0.37
    Activations Density 0.451%

    No Known Activations