© 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. 4-GEMMASCOPE-RES-16K
    11. 15772
    Prev
    Next
    INDEX
    Explanations

    symbols and structures typically used in mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.74
    Controllo
    -0.70
     Normdatei
    -0.69
     lenker
    -0.69
    Portale
    -0.67
    цездатний
    -0.66
    ArrowToggle
    -0.66
    PreferredItem
    -0.65
    XmlAccessType
    -0.64
     TestBed
    -0.64
    POSITIVE LOGITS
    }{
    0.64
    }{|
    0.59
     WebDriverWait
    0.57
    ضة
    0.56
    paddingVertical
    0.56
    ]}{
    0.56
     }{
    0.52
    devamını
    0.52
     kuri
    0.51
     vuitton
    0.51
    Activations Density 0.018%

    No Known Activations