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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 8480
    Prev
    Next
    INDEX
    Explanations

    references to XML and JSON configurations in the context of application development

    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
    TagMode
    -0.60
    RTRS
    -0.51
    tagHelperRunner
    -0.48
    GestureDetector
    -0.47
    Tikang
    -0.47
    URLEncoder
    -0.47
     Puck
    -0.46
    )}{(
    -0.46
    Hozzáférés
    -0.46
     sensation
    -0.46
    POSITIVE LOGITS
    ftagPool
    0.91
     виправивши
    0.72
     estekak
    0.69
     yaml
    0.67
    CloseOperation
    0.67
    RetentionPolicy
    0.65
     propOrder
    0.65
     препратки
    0.64
    htaccess
    0.62
    gnore
    0.62
    Activations Density 0.538%

    No Known Activations