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. 9260
    Prev
    Next
    INDEX
    Explanations

    technical annotations and framework-specific syntax in programming code

    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
    -0.81
     gynhyrchwyd
    -0.58
    onuclear
    -0.55
     [*]
    -0.50
     Vella
    -0.50
    ailleurs
    -0.49
     reta
    -0.49
    PreExecute
    -0.49
     referenties
    -0.47
    intios
    -0.47
    POSITIVE LOGITS
     onAnimation
    0.64
    []>(
    0.63
    〒
    0.58
     Мексичка
    0.57
    TextInputLayout
    0.54
    "",
    
    0.53
    TintMode
    0.53
    jectures
    0.52
     useRouter
    0.51
     access
    0.51
    Activations Density 0.068%

    No Known Activations