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. 3-GEMMASCOPE-RES-16K
    6. 11113
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related phrases that indicate connections or relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.87
     nahilalakip
    -0.85
    tvguidetime
    -0.81
     ProtoMessage
    -0.80
     surla
    -0.77
     незавершена
    -0.76
    новниш
    -0.72
    IntoConstraints
    -0.70
     kasarigan
    -0.69
     CreateTagHelper
    -0.67
    POSITIVE LOGITS
     AttributeSet
    0.57
    BufferException
    0.45
     effort
    0.45
    ,:);
    0.41
    TRIBUTE
    0.41
    DECREF
    0.41
    xfer
    0.39
     recevez
    0.39
    auxite
    0.39
     plena
    0.39
    Activations Density 0.369%

    No Known Activations