© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30754
    Prev
    Next
    INDEX
    Explanations

    terms related to accountability and consequences in professional settings

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

    scandals and controversies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.69
    SOUNDBITE
    -0.66
     Réponses
    -0.65
    TacToe
    -0.63
    AsUp
    -0.63
     HttpNotFound
    -0.61
     AssemblyCulture
    -0.61
    новништво
    -0.60
    readystatechange
    -0.60
    WebControls
    -0.59
    POSITIVE LOGITS
     scandals
    1.36
     scandal
    1.32
     controversy
    1.06
     controversies
    1.05
     scandalous
    0.98
     скан
    0.89
     Scandal
    0.88
     scand
    0.87
     Scand
    0.86
     Controversy
    0.84
    Activations Density 0.548%

    No Known Activations