© 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. 22-GEMMASCOPE-RES-16K
    11. 8283
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes, particularly those related to links and class definitions

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

    Tokens preceding HTML class/title/name attributes

    np_acts-logits-general · gemini-2.0-flash

    name="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.63
    setVerticalGroup
    -0.62
     PopupWindow
    -0.54
    PerformLayout
    -0.50
    ̍t
    -0.48
     olduğunu
    -0.48
    GOTREF
    -0.47
    SharedCtor
    -0.45
    Gambas
    -0.44
    featureID
    -0.44
    POSITIVE LOGITS
    ſelf
    0.67
     Reſ
    0.65
     Majefty
    0.64
     للمعارف
    0.63
    bibinfo
    0.62
     isComment
    0.61
    Rhestr
    0.60
    greenrobot
    0.60
     estimés
    0.60
     Inscrivez
    0.59
    Activations Density 0.093%

    No Known Activations