© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 830
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and publications

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

    journals or blogs

    np_acts-logits-general · gemini-2.0-flash

    types of publications

    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
    UserScript
    -0.64
    AnchorStyles
    -0.63
    mergeFrom
    -0.57
    AddTagHelper
    -0.55
    simum
    -0.54
     مواليد
    -0.53
    leyebilirsiniz
    -0.53
    aktery
    -0.53
    __.__
    -0.53
    atzes
    -0.52
    POSITIVE LOGITS
    Portale
    0.79
     entries
    0.69
     entry
    0.64
    */].
    0.64
     Csv
    0.59
    UITableView
    0.58
     halls
    0.58
    openConnection
    0.57
     Entry
    0.57
     Volkes
    0.57
    Activations Density 0.242%

    No Known Activations