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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13715
    Prev
    Next
    INDEX
    Explanations

    database insertion commands and structures related to data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للمعارف
    -0.95
     فريبيس
    -0.83
     utafitiHapana
    -0.80
     OFDb
    -0.77
     Pingback
    -0.74
     ComVisible
    -0.73
    ISupport
    -0.68
     gynhyrchwyd
    -0.68
     BoxDecoration
    -0.68
     autorytatywna
    -0.67
    POSITIVE LOGITS
    Искәрмәләр
    0.57
    VersionUID
    0.57
    Einzelnachweise
    0.54
    makeConstraints
    0.54
    FailureListener
    0.52
    BeginContext
    0.51
    >>;
    0.51
    onChangeText
    0.50
     correctes
    0.48
    žius
    0.47
    Activations Density 1.759%

    No Known Activations