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. 0-GEMMASCOPE-RES-16K
    6. 6403
    Prev
    Next
    INDEX
    Explanations

    references to protocols and their implementation or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    مصادر
    -0.56
    phrine
    -0.49
     `
    -0.47
    iennes
    -0.46
    sel
    -0.46
     vri
    -0.46
     mach
    -0.46
    IVA
    -0.45
    uos
    -0.45
     consultato
    -0.44
    POSITIVE LOGITS
    ()")
    0.87
    ")));
    
    0.86
    practice
    0.84
    )++;
    0.82
    Practice
    0.82
     />";
    0.81
     practice
    0.81
    دانشنامهٔ
    0.80
     protocol
    0.80
    $")
    0.80
    Activations Density 0.104%

    No Known Activations