© 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. 33-GEMMASCOPE-RES-16K
    11. 2992
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of frustration or avoidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlEnum
    -0.47
      
    -0.43
     Repairs
    -0.39
     diskon
    -0.36
    生平
    -0.34
     uș
    -0.33
     Lindgren
    -0.33
     guessing
    -0.32
    quiao
    -0.31
     administracy
    -0.31
    POSITIVE LOGITS
     Medium
    0.88
    Medium
    0.83
    medium
    0.75
     medium
    0.69
    MEDIUM
    0.64
     MEDIUM
    0.63
    — 
    0.62
    rungsseite
    0.61
     disambiguazione
    0.56
    aarrggbb
    0.55
    Activations Density 0.274%

    No Known Activations