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. 7808
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and parameters related to URIs and their associated functionalities

    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
    kuuta
    -0.62
    ]<=
    -0.60
    setVerticalGroup
    -0.55
    CloseOperation
    -0.54
    RectangleBorder
    -0.48
     الرياضيه
    -0.47
    poca
    -0.47
     rather
    -0.47
    uttavia
    -0.47
     endfor
    -0.46
    POSITIVE LOGITS
    uri
    0.89
    uris
    0.87
    UR
    0.84
    ur
    0.79
    ure
    0.74
     Italijani
    0.73
    uras
    0.71
     UR
    0.69
    URE
    0.69
    urate
    0.69
    Activations Density 2.962%

    No Known Activations