© 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. 9971
    Prev
    Next
    INDEX
    Explanations

    code structure and control flow elements

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

    The variable "j" in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    j followed by (j)

    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
     فريبيس
    -0.98
     Meksiku
    -0.47
    IBarButtonItem
    -0.46
    webElement
    -0.45
    SafeMath
    -0.45
    cise
    -0.44
    actionMode
    -0.44
    んぼ
    -0.44
    tagHelperRunner
    -0.43
    yz
    -0.43
    POSITIVE LOGITS
     j
    2.27
    j
    2.09
     J
    1.39
    J
    1.32
     job
    1.12
    𝑗
    1.01
     jobs
    0.90
    job
    0.86
    ｊ
    0.82
     Job
    0.78
    Activations Density 0.400%

    No Known Activations