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. 2958
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and question marks

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

    Comes before "By" or punctuation

    np_acts-logits-general · gemini-2.0-flash

    concluding phrases

    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
    didSet
    -0.98
     estekak
    -0.88
     ffilmiau
    -0.85
     Wiktionnaire
    -0.85
    providedIn
    -0.84
    ITERATURE
    -0.83
     BoxFit
    -0.83
    ReusableCell
    -0.82
     Vikipedi
    -0.81
    ﷺ
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.87
    ↵
    0.62
    ちなみに
    0.49
    Furthermore
    0.48
    ↵↵↵
    0.47
       
    0.47
     Furthermore
    0.45
    Ultimately
    0.43
     Ultimately
    0.43
    ​
    0.42
    Activations Density 0.793%

    No Known Activations