© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8108
    Prev
    Next
    INDEX
    Explanations

    terms related to medical studies and their methodology, particularly focusing on diagnostics and evaluations

    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
     محفوظة
    -0.48
    能在
    -0.48
    )=>{
    
    -0.48
    "?>
    -0.48
    ệc
    -0.47
    こち
    -0.47
    abetes
    -0.46
    schild
    -0.44
    elos
    -0.44
    																								
    -0.44
    POSITIVE LOGITS
     transfieras
    0.64
     Nus
    0.61
     studenti
    0.59
     dials
    0.57
     bVar
    0.56
    rungsseite
    0.56
    upsi
    0.55
    ñores
    0.54
     Utiliza
    0.54
    说
    0.54
    Activations Density 0.274%

    No Known Activations