© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12742
    Prev
    Next
    INDEX
    Explanations

    themes of personal aspirations and following dreams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.40
    тистика
    -0.39
     problemática
    -0.39
    loài
    -0.39
     gärna
    -0.39
     الاطلاع
    -0.38
    abilia
    -0.38
    dibly
    -0.38
     Modell
    -0.38
    Modell
    -0.37
    POSITIVE LOGITS
    évaluateur
    0.41
    ⓧ
    0.41
     living
    0.41
     boldly
    0.40
    living
    0.39
     coraggio
    0.39
     bold
    0.38
    currentColor
    0.38
    rungsseite
    0.37
     الحره
    0.37
    Activations Density 0.238%

    No Known Activations