© 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. 2-GEMMASCOPE-RES-16K
    11. 5844
    Prev
    Next
    INDEX
    Explanations

    expressions related to honesty and purity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rodo
    -0.36
    }^{(\
    -0.36
     pili
    -0.36
     JTextField
    -0.36
     вікісторінку
    -0.36
    pantalones
    -0.35
     JButton
    -0.35
     kasarigan
    -0.35
     définiti
    -0.35
    Noter
    -0.34
    POSITIVE LOGITS
     tail
    0.69
     honest
    0.65
     Honest
    0.61
    phy
    0.60
     tails
    0.57
    honest
    0.56
     Cancer
    0.56
    Honest
    0.55
    PHY
    0.55
     pure
    0.54
    Activations Density 0.117%

    No Known Activations