© 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. 22-GEMMASCOPE-RES-16K
    11. 763
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate leadership and statements made by executives

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

    Attribution or explanation of speech

    np_acts-logits-general · gemini-2.0-flash

    reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.85
     bezeichneter
    -0.80
    principalTable
    -0.75
    BeginContext
    -0.75
     ſeveral
    -0.74
     lenker
    -0.73
    Portail
    -0.72
     accuse
    -0.70
     fometimes
    -0.70
     accusing
    -0.70
    POSITIVE LOGITS
     commented
    0.99
     stated
    0.94
     comments
    0.83
     comment
    0.82
     expressed
    0.78
     revealed
    0.76
     explained
    0.76
     commenting
    0.72
     explains
    0.72
     Comment
    0.69
    Activations Density 0.137%

    No Known Activations