© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 568
    Prev
    Next
    INDEX
    Explanations

    punctuation characters, particularly closing parentheses and curly braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     विश्वसनीयता
    -0.75
    ReusableCell
    -0.69
     Dwight
    -0.67
     Mero
    -0.65
     Behold
    -0.62
     Eud
    -0.62
     ―――――
    -0.61
     Cicero
    -0.60
     Prun
    -0.60
     Annika
    -0.59
    POSITIVE LOGITS
    __':
    
    0.99
    __':
    0.97
    niająca
    0.76
    __":
    0.76
    didSet
    0.71
    __":
    
    0.70
    <bos>
    0.69
    BeginContext
    0.67
     AssemblyProduct
    0.66
    saraba
    0.65
    Activations Density 0.129%

    No Known Activations