© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6331
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their attributes

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

    "idx" followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    "Andrew" variants following "ing" or preceding "idx"

    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
     Gamb
    -0.68
    CEP
    -0.67
     Mansfield
    -0.61
     Quin
    -0.61
     CEP
    -0.60
     Oppen
    -0.59
     Dickinson
    -0.59
     Pl
    -0.59
    Coul
    -0.57
    cep
    -0.57
    POSITIVE LOGITS
     Andrew
    1.45
    Andrew
    1.25
     Andrews
    1.22
     andrew
    1.21
     Andy
    1.13
     ANDREW
    1.11
    andrew
    1.08
    ANDREW
    1.07
    Andy
    1.00
    Andrews
    0.99
    Activations Density 0.505%

    No Known Activations