© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10107
    Prev
    Next
    INDEX
    Explanations

    contradictory descriptions or contrasting appearances versus reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сіб
    -0.50
    жере
    -0.50
    ্ষ
    -0.49
    PROPS
    -0.48
     libero
    -0.48
     enten
    -0.48
    Either
    -0.48
    either
    -0.48
     spéciale
    -0.47
     vlastní
    -0.47
    POSITIVE LOGITS
     outwardly
    1.08
     seeming
    1.05
    看似
    1.02
     apparente
    1.02
    Appearances
    0.97
     decep
    0.94
    一見
    0.94
     seemingly
    0.92
     appearances
    0.92
     Appearances
    0.89
    Activations Density 0.195%

    No Known Activations