© 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. 6562
    Prev
    Next
    INDEX
    Explanations

    programming constructs and identifiers related to server functions and message handling

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     '\\;'
    -0.70
    tagHelperRunner
    -0.68
    AndEndTag
    -0.65
    KommentareTeilen
    -0.63
     незавершена
    -0.62
     صوتيه
    -0.62
    úgó
    -0.59
     Normdatei
    -0.59
    contentLoaded
    -0.59
    thebibliography
    -0.58
    POSITIVE LOGITS
     but
    1.03
     rather
    0.89
     instead
    0.85
     But
    0.83
    But
    0.81
    but
    0.74
    instead
    0.74
    rather
    0.73
     Tetapi
    0.71
     Rather
    0.67
    Activations Density 0.204%

    No Known Activations