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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 22
    Prev
    Next
    INDEX
    Explanations

    technical concepts related to data handling and persistence in computing

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

    multi-lingual terms and code

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ?
    -0.52
     通販
    -0.52
    !
    -0.51
     rechange
    -0.50
    usercontent
    -0.46
    Viungo
    -0.46
    memoized
    -0.45
    EndContext
    -0.45
    modelBuilder
    -0.44
    حوالہ
    -0.44
    POSITIVE LOGITS
     NSCoder
    0.80
     للاسماء
    0.80
    تقاوى
    0.80
    ########.
    0.79
    存于互联网档案馆
    0.76
     utafitiHapana
    0.74
     Insee
    0.68
     дописавши
    0.65
     ComVisible
    0.64
     autorytatywna
    0.63
    Activations Density 0.010%

    No Known Activations