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. 20-GEMMASCOPE-RES-16K
    6. 4021
    Prev
    Next
    INDEX
    Explanations

    URLs and web resource paths

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

    URLs, especially those with schemes (HTTP, HTTPS, AMQP)

    np_acts-logits-general · gemini-2.0-flash

    URL schemes (http, https)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.54
    ؤلاء
    -0.51
     onCreateView
    -0.51
    ulemon
    -0.51
     ExecuteAsync
    -0.51
     ModelRenderer
    -0.49
     taxes
    -0.49
    PropertyGroup
    -0.49
     Taxes
    -0.49
    AttributeSet
    -0.46
    POSITIVE LOGITS
    httphttps
    0.85
    Scheme
    0.80
    scheme
    0.78
    https
    0.77
     scheme
    0.74
     Scheme
    0.70
     https
    0.69
    SCHEME
    0.68
    http
    0.67
     schemes
    0.66
    Activations Density 0.188%

    No Known Activations