© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106070
    Prev
    Next
    INDEX
    Explanations

    references to biases and limitations in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.57
    ModelSerializer
    -0.52
    tagHelperRunner
    -0.51
    المناصب
    -0.51
    OGND
    -0.50
    uxxxx
    -0.49
    jsonwebtoken
    -0.47
    arbon
    -0.47
    phor
    -0.47
     surla
    -0.46
    POSITIVE LOGITS
     errors
    0.45
     factors
    0.42
     biais
    0.40
     possible
    0.39
     error
    0.38
     válido
    0.35
     biases
    0.35
     procedures
    0.35
     errores
    0.35
     bias
    0.35
    Activations Density 0.162%

    No Known Activations