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. 5-GEMMASCOPE-RES-16K
    6. 15995
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft-related components and libraries in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.82
    ?}",
    -0.77
    SharedDtor
    -0.73
     ModelRenderer
    -0.72
     gawas
    -0.72
     tartalomajánló
    -0.72
    ]));
    
    -0.71
    Vidite
    -0.71
    contentLoaded
    -0.71
    ']));
    -0.69
    POSITIVE LOGITS
     متعلقه
    0.54
     houſe
    0.52
    Iden
    0.50
     Zä
    0.47
     répon
    0.47
    tagHelperRunner
    0.46
    shutil
    0.46
     vän
    0.46
     ſame
    0.45
    lück
    0.45
    Activations Density 0.007%

    No Known Activations