© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12527
    Prev
    Next
    INDEX
    Explanations

    variable assignments and their operations in code

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

    PHP code related to returning values or checking conditions

    np_acts-logits-general · gemini-2.0-flash

    conditional expressions and returns

    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
     Efq
    -0.75
     Theſe
    -0.71
     $_"
    -0.66
     myſelf
    -0.65
     Houſe
    -0.63
     Reſ
    -0.62
     Monfieur
    -0.62
    LEGGI
    -0.61
    RectangleBorder
    -0.60
     Diſ
    -0.60
    POSITIVE LOGITS
    (!
    1.05
     (!
    1.01
     !
    1.00
     if
    0.97
     ((!
    0.93
    if
    0.83
     whether
    0.82
    !
    0.77
     If
    0.73
     (
    0.72
    Activations Density 0.110%

    No Known Activations