© 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. 141
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and partnership in various contexts

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

    Prepositions "in" and "on"

    np_acts-logits-general · gemini-2.0-flash

    states, case, or a

    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
    WebVitals
    -0.56
    Spending
    -0.56
     confiar
    -0.56
     Spending
    -0.55
     oír
    -0.55
    awtextra
    -0.54
    一目
    -0.53
     Verwendung
    -0.53
     застосування
    -0.52
    Having
    -0.52
    POSITIVE LOGITS
     improving
    1.30
     ensuring
    1.21
    improving
    1.17
     enhancing
    1.14
     Improving
    1.09
    Improving
    1.07
     solving
    1.04
     perfecting
    1.03
     securing
    1.01
     preparing
    1.01
    Activations Density 0.616%

    No Known Activations