© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12386
    Prev
    Next
    INDEX
    Explanations

    topics related to achievement and rewards, particularly in gamification contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.87
     المعيارى
    -0.77
     Roskov
    -0.73
    OGND
    -0.72
    -------------</
    -0.71
    WriteTagHelper
    -0.70
    RTLR
    -0.65
     surla
    -0.65
    ніципалі
    -0.62
    LayoutPanel
    -0.61
    POSITIVE LOGITS
    readystatechange
    0.72
     achievement
    0.71
     completion
    0.66
     Completion
    0.63
     Achievement
    0.61
     achievements
    0.60
     requirements
    0.60
     attainment
    0.59
     reward
    0.59
    πον
    0.57
    Activations Density 0.299%

    No Known Activations