© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14000
    Prev
    Next
    INDEX
    Explanations

    expressions related to effort and hard work in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.73
    principalColumn
    -0.73
     snippetHide
    -0.72
     Paglinawan
    -0.68
    AndEndTag
    -0.68
    oredCriteria
    -0.62
     ujednoznacz
    -0.62
     useAppContext
    -0.61
     initComponents
    -0.61
    onViewCreated
    -0.61
    POSITIVE LOGITS
     painstaking
    0.71
     efforts
    0.68
     effort
    0.66
     esfuerzo
    0.61
    努力
    0.56
     esfuerzos
    0.53
     Efforts
    0.52
     esforço
    0.52
    efforts
    0.51
     hard
    0.50
    Activations Density 0.268%

    No Known Activations