© 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. 30-GEMMASCOPE-RES-16K
    11. 15541
    Prev
    Next
    INDEX
    Explanations

    phrases related to limitations and biases in research studies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    before possible error sources

    np_acts-logits-general · gemini-2.0-flash

    errors, noise, contamination, bias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     indented
    -0.47
     Roskov
    -0.45
    rungsseite
    -0.44
    ResumeLayout
    -0.43
    EndContext
    -0.42
    opted
    -0.41
    addGap
    -0.41
     Asser
    -0.40
    NullCheck
    -0.40
     отре
    -0.40
    POSITIVE LOGITS
     contamination
    0.78
     inherent
    0.73
     inaccuracies
    0.72
     errors
    0.72
     noise
    0.69
     contamin
    0.69
     uncertainties
    0.69
     confounding
    0.68
     erreurs
    0.68
     unavoidable
    0.67
    Activations Density 2.661%

    No Known Activations