© 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. 35-GEMMASCOPE-RES-16K
    11. 16116
    Prev
    Next
    INDEX
    Explanations

    keywords related to concepts of morality and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.56
     actionMode
    -0.40
    ंदीखरीदारी
    -0.39
    IntoConstraints
    -0.39
    Autoritní
    -0.39
    DOCTYPE
    -0.36
     ditto
    -0.36
    maier
    -0.36
    actionMode
    -0.35
     colspan
    -0.35
    POSITIVE LOGITS
    fulness
    2.25
    ful
    2.19
    FUL
    2.02
    full
    1.93
    fully
    1.92
    FULL
    1.60
    FULLY
    1.51
    Ful
    1.50
     ful
    1.45
    fuls
    1.44
    Activations Density 0.217%

    No Known Activations