© 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. 7-GEMMASCOPE-RES-16K
    11. 12479
    Prev
    Next
    INDEX
    Explanations

    sequences of letters or numbers that indicate hierarchical classifications or categories in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للمعارف
    -0.50
    rungsseite
    -0.50
    GEBURTS
    -0.49
    ंदीखरीदारी
    -0.47
     tartalomajánló
    -0.45
    oa̍t
    -0.43
    AnchorTagHelper
    -0.43
     snippetHide
    -0.43
    transQ
    -0.42
    Демографія
    -0.42
    POSITIVE LOGITS
     iprot
    0.50
    \{\\
    0.44
     oprot
    0.44
    sitis
    0.41
     currentState
    0.39
     deviceId
    0.39
    AddAttribute
    0.39
     bookId
    0.39
     governments
    0.39
     oligonucleotide
    0.39
    Activations Density 0.943%

    No Known Activations