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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6080
    Prev
    Next
    INDEX
    Explanations

    elements related to data visualization, particularly in plotting contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with plot/plotting functions

    np_acts-logits-general · gemini-2.0-flash

    plotting functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.66
    glTexCoord
    -0.59
     поступа
    -0.57
    \{\\
    -0.57
    geschlossen
    -0.56
    GEBURTSDATUM
    -0.54
     }^{(
    -0.52
     mencu
    -0.52
    /***/
    -0.51
    getOutputStream
    -0.51
    POSITIVE LOGITS
     pyplot
    0.70
     matplotlib
    0.67
     plt
    0.66
    plt
    0.65
    lichung
    0.62
    plot
    0.62
    ROIT
    0.60
     pylab
    0.60
    pyplot
    0.59
     plots
    0.57
    Activations Density 0.107%

    No Known Activations