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. 11217
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    ultati
    -0.67
    <bos>
    -0.65
     continúas
    -0.59
    Chham
    -0.56
    CreateMap
    -0.56
    Sag
    -0.53
    owanym
    -0.53
     kuru
    -0.51
     XNUMX
    -0.51
     Fairview
    -0.51
    POSITIVE LOGITS
    MessageOf
    0.83
    GEBURTSDATUM
    0.82
     <=",
    0.81
    SequentialGroup
    0.80
     ویکی‌آمباردا
    0.74
    __':
    
    0.74
    __':
    0.72
    +#+#
    0.71
     protoimpl
    0.70
    brities
    0.67
    Activations Density 0.058%

    No Known Activations