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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14708
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their occurrences in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.87
     Reſ
    -0.82
     Conſ
    -0.81
     Anſ
    -0.76
     pleaſure
    -0.76
    GEBURTSDATUM
    -0.75
     oprot
    -0.75
     ſche
    -0.74
     itſelf
    -0.74
     kaarangay
    -0.73
    POSITIVE LOGITS
     Jr
    0.53
    っていると
    0.51
     and
    0.51
    っていたので
    0.50
    gemaakt
    0.50
     et
    0.47
    ึกษา
    0.47
     Archer
    0.46
     collaborateurs
    0.46
    ;">
    
    0.45
    Activations Density 0.117%

    No Known Activations