© 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. 1-GEMMASCOPE-RES-16K
    11. 8389
    Prev
    Next
    INDEX
    Explanations

    terms related to technical expertise and professionalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icksburg
    -0.50
    TypedDataSet
    -0.48
     كومونز
    -0.47
     Arbeitgeber
    -0.46
     <>",
    -0.46
    crombie
    -0.43
     Decke
    -0.43
    VYMaps
    -0.42
     Neubau
    -0.42
     gruesa
    -0.41
    POSITIVE LOGITS
     Technical
    1.41
     technical
    1.38
    Technical
    1.34
     Tech
    1.29
    Tech
    1.21
    technical
    1.20
     TECHNICAL
    1.18
     TECH
    1.09
     техни
    1.05
     TECHN
    1.04
    Activations Density 0.213%

    No Known Activations