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. 12748
    Prev
    Next
    INDEX
    Explanations

    proper names and their associated details

    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
     Doyle
    -0.92
     Hatt
    -0.89
    ]";
    -0.78
     Jard
    -0.77
    ]");
    -0.77
    calaureate
    -0.77
    Jard
    -0.76
     Toma
    -0.76
     Krueger
    -0.75
     Stel
    -0.74
    POSITIVE LOGITS
     تضيفلها
    1.03
     Pore
    0.90
     McGowan
    0.87
     Demet
    0.86
     defaultstate
    0.81
     electrolytes
    0.80
     Polly
    0.80
    Tracce
    0.79
     Eury
    0.77
     inéd
    0.76
    Activations Density 2.282%

    No Known Activations