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. 12139
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions in sentence structures

    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
    laş
    -0.63
    owicz
    -0.63
    zeme
    -0.61
    gelen
    -0.59
    peč
    -0.59
     useContext
    -0.58
     staat
    -0.58
    ętr
    -0.57
    hlon
    -0.57
    Tikang
    -0.56
    POSITIVE LOGITS
     /\.
    1.00
     И
    0.84
     и
    0.84
    И
    0.79
    InvalidProtocol
    0.79
     і
    0.78
    ArgsConstructor
    0.72
    и
    0.72
    EdgeInsets
    0.71
     ostavi
    0.70
    Activations Density 0.012%

    No Known Activations