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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68375
    Prev
    Next
    INDEX
    Explanations

    method calls and asynchronous operations in code

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

    group by having count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tagHelperRunner
    -0.44
    ThroughAttribute
    -0.40
     widers
    -0.38
    userdetails
    -0.37
    webElementGuid
    -0.35
    кипе
    -0.35
     onCancelled
    -0.35
    styleable
    -0.35
    رشف
    -0.35
    互联网档案馆
    -0.34
    POSITIVE LOGITS
     nakalista
    0.61
    WebVitals
    0.52
    RectangleBorder
    0.51
    InputBorder
    0.49
    KommentareTeilen
    0.47
    Gambas
    0.47
     viewDidLoad
    0.47
    icksburg
    0.47
    IsContent
    0.46
    gestone
    0.46
    Activations Density 0.002%

    No Known Activations