© 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. 1335
    Prev
    Next
    INDEX
    Explanations

    elements related to introspection and contemplation of ideas and memories

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

    "Thoughts", "images", or "ideas" in text

    np_acts-logits-general · gemini-2.0-flash

    mental images or ideas

    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
    enumi
    -0.64
     couvert
    -0.55
     étui
    -0.53
     conocemos
    -0.53
    Jeografia
    -0.52
    isRequired
    -0.52
    Chham
    -0.51
     misura
    -0.50
    fani
    -0.49
     сре
    -0.49
    POSITIVE LOGITS
     thoughts
    0.85
    bidden
    0.78
     flashed
    0.78
     vivid
    0.75
    脑海
    0.73
     flashes
    0.73
     images
    0.73
     Thoughts
    0.71
    Thoughts
    0.70
    thoughts
    0.69
    Activations Density 0.230%

    No Known Activations