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. 4202
    Prev
    Next
    INDEX
    Explanations

    ellipses or interruptions in dialogue

    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
     BorderRadius
    -0.72
     myſelf
    -0.67
     itſelf
    -0.64
     themſelves
    -0.63
     Efq
    -0.62
     estimés
    -0.61
    UrlResolution
    -0.59
    ỗi
    -0.58
     perfons
    -0.58
     Majefty
    -0.57
    POSITIVE LOGITS
     disambiguazione
    0.86
    rungsseite
    0.72
    ***********
    0.62
    MemoryWarning
    0.61
    **********
    0.61
    )]);
    0.59
    -...
    0.57
    unknownFields
    0.57
    );?>
    0.56
    ...');
    0.56
    Activations Density 0.108%

    No Known Activations