© 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. 20-GEMMASCOPE-RES-16K
    11. 2514
    Prev
    Next
    INDEX
    Explanations

    statements related to decisions and their implications

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

    Contractions of "is" or "was"

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flavour
    -0.60
    coloured
    -0.58
     şi
    -0.57
    colour
    -0.57
    InstanceState
    -0.56
     Honour
    -0.56
     nämlich
    -0.55
     unauthorised
    -0.55
    gatsby
    -0.55
     honour
    -0.54
    POSITIVE LOGITS
    RegressionTest
    0.60
    DockStyle
    0.58
     consultato
    0.56
    TextBoxColumn
    0.54
     Вікіпе
    0.53
    AccessorTable
    0.52
     Fiber
    0.52
     SqlConnection
    0.52
    nasium
    0.51
    Și
    0.51
    Activations Density 0.162%

    No Known Activations