© 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. 24-GEMMASCOPE-RES-16K
    11. 8370
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to amendments and judicial processes

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

    after "its," "or," "amendment," or "inhibition."

    np_acts-logits-general · gemini-2.0-flash

    modification or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bonté
    -0.73
     editados
    -0.72
     dissipate
    -0.72
     Installing
    -0.72
    Installing
    -0.71
     cheated
    -0.71
     Evaluating
    -0.71
     leçon
    -0.70
     измени
    -0.69
     migrated
    -0.69
    POSITIVE LOGITS
     relegation
    0.56
     fortification
    0.55
    cellation
    0.54
    ilitation
    0.54
    Anywhere
    0.54
    collation
    0.52
     integration
    0.52
     regulation
    0.51
     modification
    0.51
     titration
    0.51
    Activations Density 2.148%

    No Known Activations