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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9253
    Prev
    Next
    INDEX
    Explanations

    specific anatomical components related to tibial and femoral implants

    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
     Apa
    -0.82
     Shale
    -0.73
     StatelessWidget
    -0.72
     Viber
    -0.70
    NUMX
    -0.70
     Mamma
    -0.70
    żdy
    -0.70
    romyalgia
    -0.70
    ();?>
    -0.69
    _{*}
    -0.69
    POSITIVE LOGITS
     Astrid
    0.71
    serviceWorker
    0.70
     Dag
    0.68
     Ore
    0.66
    SCO
    0.66
     cors
    0.65
     Cors
    0.65
     Dal
    0.64
    Tokens
    0.64
    Astrid
    0.64
    Activations Density 0.765%

    No Known Activations