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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10775
    Prev
    Next
    INDEX
    Explanations

    instances of the term "rejected" and related concepts of denial or dismissal

    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
     kjø
    -0.42
     fær
    -0.38
    frastructure
    -0.38
    gjenge
    -0.38
     Enumerable
    -0.37
    complexType
    -0.37
     mahdol
    -0.37
    ůže
    -0.36
     internetowa
    -0.36
    makeConstraints
    -0.35
    POSITIVE LOGITS
     omitted
    0.96
     rejected
    0.82
     ignored
    0.81
     unnoticed
    0.79
     neglected
    0.77
     Rejected
    0.75
    rejected
    0.69
     overlooked
    0.69
    ignored
    0.65
    MathML
    0.65
    Activations Density 0.338%

    No Known Activations