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. 6399
    Prev
    Next
    INDEX
    Explanations

    specific patent numbers and document titles related to inventions

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

    U.S. patent numbers

    np_acts-logits-general · gemini-2.0-flash

    U.S. Pat. No. discloses

    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
    eavour
    -0.59
    </em>
    -0.49
    </strong>
    -0.49
    <strong>
    -0.46
    ğren
    -0.46
    Референце
    -0.44
    thalene
    -0.44
    g
    -0.44
     After
    -0.43
     ت
    -0.42
    POSITIVE LOGITS
     Houſe
    0.83
     houſe
    0.82
     Anſ
    0.73
    AccessorTable
    0.73
    andExpect
    0.71
    ^(@)
    0.70
     nakalista
    0.69
     تضيفلها
    0.65
    ngdoc
    0.65
     */;
    0.64
    Activations Density 0.202%

    No Known Activations