Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 6149
    Prev
    Next
    INDEX
    Explanations

    terms related to sports playoffs and medical cures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openzeppelin
    -0.82
     lenker
    -0.78
    __*/
    -0.78
    mybatisplus
    -0.68
     TMS
    -0.66
     Engra
    -0.66
     TPE
    -0.66
     OBO
    -0.65
     jScrollPane
    -0.65
     Instrum
    -0.64
    POSITIVE LOGITS
     cure
    0.91
     Cure
    0.85
    Cube
    0.84
     earthquake
    0.84
     Cube
    0.83
     cube
    0.82
     ballot
    0.76
     Earthquake
    0.73
     playoff
    0.73
    cube
    0.73
    Activations Density 0.153%

    No Known Activations