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. 25-GEMMASCOPE-RES-16K
    6. 4290
    Prev
    Next
    INDEX
    Explanations

    provides information about custom print orders and shipping details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.72
    RenderAtEndOf
    -0.66
    下载附件
    -0.64
     '\\;'
    -0.63
     kasarigan
    -0.62
    BagConstraints
    -0.61
    GetEnumerator
    -0.61
    כשיו
    -0.59
    DockStyle
    -0.58
    Referències
    -0.57
    POSITIVE LOGITS
     personalization
    0.83
     personalisation
    0.72
     customization
    0.71
    PERSONAL
    0.70
     personalize
    0.69
     personalized
    0.68
     Customization
    0.68
     PERSONAL
    0.68
     Personalized
    0.67
     customizations
    0.66
    Activations Density 0.085%

    No Known Activations