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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13164
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements often used in programming or markup

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

    Values with hyphens and units

    np_acts-logits-general · gemini-2.0-flash

    if predetermined location

    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
     Osborn
    -0.79
     Sando
    -0.74
     Colbert
    -0.72
     AssemblyTitle
    -0.72
     Klee
    -0.70
    extAlignment
    -0.69
     Papi
    -0.68
    sene
    -0.67
     Leone
    -0.66
    piram
    -0.66
    POSITIVE LOGITS
     Landis
    0.62
     Odyssey
    0.61
     Moha
    0.60
    ि
    0.57
    al
    0.57
    א
    0.56
     Moran
    0.54
    er
    0.52
     Burma
    0.52
     Radha
    0.52
    Activations Density 1.186%

    No Known Activations