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. 13-GEMMASCOPE-RES-16K
    6. 10102
    Prev
    Next
    INDEX
    Explanations

    code-related actions or functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setupUi
    -0.57
    Handlung
    -0.50
    .”
    -0.46
    ,”
    -0.46
    downcase
    -0.45
    "]];
    -0.45
    ();*/
    -0.45
    ('');
    
    -0.44
     kup
    -0.43
     faid
    -0.43
    POSITIVE LOGITS
     виправивши
    0.92
    expandindo
    0.83
     ExecuteAsync
    0.76
    Geplaatst
    0.74
     Normdatei
    0.72
     bezeichneter
    0.71
    存于互联网档案馆
    0.71
     referenties
    0.70
     AspNetCore
    0.69
    Datuak
    0.69
    Activations Density 1.240%

    No Known Activations