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. 2-GEMMASCOPE-RES-16K
    6. 6676
    Prev
    Next
    INDEX
    Explanations

    specific medical terminology and related characteristics

    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
     elegant
    -0.87
     robust
    -0.86
     majestic
    -0.83
    elegant
    -0.82
    robust
    -0.82
     beautiful
    -0.77
     delicate
    -0.76
     gorgeous
    -0.75
     cool
    -0.74
    Robust
    -0.74
    POSITIVE LOGITS
     للمعارف
    0.82
    PROLOG
    0.68
    UserScript
    0.65
    rungsseite
    0.65
    perfusion
    0.63
     quoque
    0.61
     réellement
    0.60
     חיצוניים
    0.60
     peor
    0.59
    chability
    0.57
    Activations Density 4.057%

    No Known Activations