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. 16-GEMMASCOPE-RES-16K
    6. 12927
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and entities involved in legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    [Word] to [verb] construction

    np_acts-logits-general · gemini-2.0-flash

    entity followed by to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -1.00
    "])
    
    -0.92
    "]).
    -0.92
    "]);
    
    -0.90
    ()");
    -0.86
     Roskov
    -0.86
    /");
    -0.86
    "]),
    -0.85
     "").
    -0.82
    ."));
    -0.82
    POSITIVE LOGITS
     to
    0.52
     nationales
    0.48
     darum
    0.46
    câ
    0.46
     abbiano
    0.45
     themselves
    0.45
     exceptionnelle
    0.44
     assolu
    0.43
     addirittura
    0.43
     that
    0.43
    Activations Density 0.386%

    No Known Activations