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. 0-GEMMASCOPE-RES-16K
    6. 3394
    Prev
    Next
    INDEX
    Explanations

    instances of the word "skip" and variations related to skipping or omitting content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.79
    ագրություններ
    -0.73
    Crossref
    -0.70
    CppCodeGen
    -0.70
    enumii
    -0.68
    .*")]
    -0.65
    LogFactory
    -0.61
    TokenNameLBRACE
    -0.61
     Leyden
    -0.61
     createState
    -0.60
    POSITIVE LOGITS
     propOrder
    0.69
     Prof
    0.67
     lecturer
    0.57
     skipped
    0.57
     professor
    0.53
    ;}
    
    0.53
     Charter
    0.53
     era
    0.52
    ++;
    
    0.52
     skip
    0.52
    Activations Density 0.102%

    No Known Activations