Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1943
    Prev
    Next
    INDEX
    Explanations

    phrases indicating challenges and perseverance in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     Indeed
    -0.81
    Perhaps
    -0.75
    Herzliche
    -0.74
     Perhaps
    -0.74
     precisely
    -0.72
     portanto
    -0.70
    Indeed
    -0.69
     effectivement
    -0.69
    прочем
    -0.68
    ねば
    -0.68
    POSITIVE LOGITS
    WebServlet
    0.74
    Geplaatst
    0.69
     BoxDecoration
    0.68
    contentLoaded
    0.67
     kinda
    0.67
     yeah
    0.63
     idk
    0.63
     MainAxisSize
    0.61
     initComponents
    0.61
    RectangleBorder
    0.61
    Activations Density 0.245%

    No Known Activations