Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-65K
    6. 58388
    Prev
    Next
    INDEX
    Explanations

    characters or symbols used in dialogue or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.54
    紆
    -0.51
    :✨
    -0.51
    meno
    -0.50
    ẵn
    -0.50
    AddTagHelper
    -0.49
    ukone
    -0.49
     básicas
    -0.48
     годах
    -0.48
    ünde
    -0.47
    POSITIVE LOGITS
    ՚
    0.91
    ’
    0.86
    '
    0.75
    
    0.75
     MonoBehaviour
    0.73
    FontStyle
    0.72
    $'
    0.72
    \'
    0.72
     getItemId
    0.71
    rillation
    0.71
    Activations Density 0.038%

    No Known Activations