© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2655
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts that describe something as "perfect."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "perfect"

    np_acts-logits-general · gemini-2.0-flash

    perfect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inscrivez
    -0.47
     Komunikasi
    -0.47
     informée
    -0.46
    ksamkeit
    -0.45
     bileklik
    -0.43
     bancaire
    -0.43
     Shrub
    -0.43
     bougies
    -0.42
    laught
    -0.42
     empresas
    -0.42
    POSITIVE LOGITS
     perfect
    2.13
    perfect
    2.08
    Perfect
    1.98
     PERFECT
    1.91
     Perfect
    1.91
    PERFECT
    1.77
     perfecto
    1.64
     perfecta
    1.60
     perfeito
    1.56
     perfe
    1.51
    Activations Density 0.049%

    No Known Activations