© 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 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. 4919
    Prev
    Next
    INDEX
    Explanations

    numerical values related to study results or data points

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

    Numbers within a larger value

    np_acts-logits-general · gemini-2.0-flash

    thousand, thousands

    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
    اند
    -0.50
     ten
    -0.45
    stab
    -0.41
    Fifteen
    -0.41
     Fifteen
    -0.41
    oni
    -0.41
    rotech
    -0.41
     net
    -0.40
     herum
    -0.40
     escalera
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    0.93
     thousand
    0.92
     فريبيس
    0.84
    CppMethod
    0.83
    ########.
    0.83
     autorytatywna
    0.81
    adpleegd
    0.80
     propOrder
    0.80
    IUrlHelper
    0.79
     thousands
    0.78
    Activations Density 1.007%

    No Known Activations