© 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. 12398
    Prev
    Next
    INDEX
    Explanations

    references to hard work and perseverance, particularly in personal achievements

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

    effort and hard work

    np_acts-logits-general · gemini-2.0-flash

    work and effort

    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
     TextInputType
    -0.67
    InjectAttribute
    -0.56
     occafion
    -0.54
     DialogInterface
    -0.53
    sidemargin
    -0.53
     htons
    -0.52
     Méd
    -0.52
    webElement
    -0.49
    reactstrap
    -0.49
    IActionResult
    -0.47
    POSITIVE LOGITS
     effort
    1.90
    effort
    1.64
     dedication
    1.58
     efforts
    1.56
     Effort
    1.48
     esfuerzo
    1.44
    Effort
    1.41
    efforts
    1.39
     esforço
    1.31
     toil
    1.31
    Activations Density 0.366%

    No Known Activations