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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 6651
    Prev
    Next
    INDEX
    Explanations

    references to organs and organelles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.75
     doInBackground
    -0.73
     StatelessWidget
    -0.72
    पया
    -0.72
     nô
    -0.71
    følgelig
    -0.70
     fű
    -0.67
    antMatchers
    -0.67
    Castell
    -0.67
     Himo
    -0.64
    POSITIVE LOGITS
     organ
    1.30
    organ
    1.02
     Organ
    0.90
     ORGAN
    0.76
     organs
    0.75
    Organ
    0.75
     órgano
    0.69
     Op
    0.69
     optim
    0.68
     Organs
    0.68
    Activations Density 0.041%

    No Known Activations