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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8756
    Prev
    Next
    INDEX
    Explanations

    conjunctions or sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CWE
    -0.64
    URLException
    -0.61
     InputDecoration
    -0.61
     BoxDecoration
    -0.59
    ContentAsync
    -0.59
    
    -0.55
    AsUp
    -0.55
    IVEREF
    -0.51
    :✨
    -0.50
    出版年
    -0.50
    POSITIVE LOGITS
    weebly
    0.78
    blogspot
    0.75
    wix
    0.67
    com
    0.66
    ning
    0.63
    wordpress
    0.60
     szóci
    0.57
    squares
    0.57
    files
    0.53
    org
    0.53
    Activations Density 0.175%

    No Known Activations