© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6065
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of rejecting or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setViewportView
    -0.48
    Hentet
    -0.46
    HasAnnotation
    -0.46
    Autoritní
    -0.46
    zzleHttp
    -0.46
    
    -0.46
    InitVars
    -0.45
    WaitGroup
    -0.44
    getRuntime
    -0.43
    autoreleasepool
    -0.42
    POSITIVE LOGITS
     reject
    3.61
     rejection
    3.48
     rejected
    3.41
     rejecting
    3.33
     rejects
    3.27
     Reject
    3.27
    reject
    3.22
     Rejection
    3.17
    Reject
    3.06
     Rejected
    2.88
    Activations Density 0.144%

    No Known Activations