© 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. 442
    Prev
    Next
    INDEX
    Explanations

    references to advanced technology or machinery in a sci-fi context

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

    voyager or system

    np_acts-logits-general · gemini-2.0-flash

    Voyager or scanner descriptions

    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
     paesi
    -0.56
     popolari
    -0.55
     mágico
    -0.53
     mágica
    -0.52
     dq
    -0.50
     onOptions
    -0.49
    ytale
    -0.47
     rispar
    -0.47
    MockMvc
    -0.46
     magique
    -0.46
    POSITIVE LOGITS
    GenerationType
    0.81
     scanners
    0.73
     ship
    0.70
    canner
    0.69
     scanner
    0.68
     scans
    0.68
     override
    0.67
     Scanner
    0.67
     cyber
    0.66
     scan
    0.66
    Activations Density 0.566%

    No Known Activations