© 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. 27-GEMMASCOPE-RES-16K
    11. 6812
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "the" in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שני
    -0.43
    Nhưng
    -0.41
     COSTS
    -0.40
     potentialities
    -0.40
    sofá
    -0.40
    pectives
    -0.40
    ukone
    -0.40
     ander
    -0.40
    raszam
    -0.40
    קש
    -0.40
    POSITIVE LOGITS
     same
    0.59
     كومونز
    0.50
    enderror
    0.50
     only
    0.49
     mijne
    0.47
     epitome
    0.46
     equivalent
    0.46
    เดียว
    0.46
     least
    0.45
     best
    0.43
    Activations Density 0.223%

    No Known Activations