© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6893
    Prev
    Next
    INDEX
    Explanations

    clinical terms related to patient care and examination devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Different states or modes

    np_acts-logits-general · gemini-2.0-flash

    positions, modes, states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onItemClick
    -0.54
     addTo
    -0.43
    blazer
    -0.43
     bulletin
    -0.43
     quant
    -0.42
    примеча
    -0.42
    glDelete
    -0.42
    lectic
    -0.41
    rifuge
    -0.41
    zionata
    -0.41
    POSITIVE LOGITS
     mode
    0.95
    UIControlState
    0.92
     modes
    0.85
     режим
    0.82
    DeleteBehavior
    0.80
     حالت
    0.80
     state
    0.80
     states
    0.79
    styleType
    0.77
    モード
    0.76
    Activations Density 0.968%

    No Known Activations