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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 4376
    Prev
    Next
    INDEX
    Explanations

    instances of special characters and formatting used in programming or markup languages

    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
     depoz
    -0.56
    fähig
    -0.51
    ested
    -0.51
    Dexter
    -0.51
    angue
    -0.51
     SIMBAD
    -0.51
    另一种
    -0.51
     Eastwood
    -0.50
     zile
    -0.49
    ↵↵
    -0.49
    POSITIVE LOGITS
    клопе
    0.92
    ViewFeatures
    0.78
     rospy
    0.78
    LLocation
    0.76
    पया
    0.73
    tagHelperRunner
    0.72
    WEBPACK
    0.71
    copg
    0.70
     &___
    0.69
    SuccessListener
    0.68
    Activations Density 0.012%

    No Known Activations