© 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. 414
    Prev
    Next
    INDEX
    Explanations

    terms related to historical political processes and decisions

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

    followed by commas

    np_acts-logits-general · gemini-2.0-flash

    formal statements and declarations

    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
    脚注の使い方
    -0.92
     transitioning
    -0.77
     vectorielles
    -0.77
     transitioned
    -0.76
     proactively
    -0.74
     للاسماء
    -0.73
     timeframe
    -0.71
     seamlessly
    -0.71
     prioritizing
    -0.71
     prioritize
    -0.71
    POSITIVE LOGITS
     muß
    0.67
     doubtless
    0.60
     müßte
    0.60
     Daß
    0.60
     daß
    0.59
     skall
    0.59
     mußte
    0.59
     hitherto
    0.58
     consequent
    0.58
     läßt
    0.57
    Activations Density 1.619%

    No Known Activations