© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8875
    Prev
    Next
    INDEX
    Explanations

    emotional states and qualities

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

    difficulty or excessiveness

    np_acts-logits-general · gemini-2.0-flash

    multilingual quantifiers

    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
     AssemblyProduct
    -0.77
    interopRequire
    -0.75
    RegistryLite
    -0.70
     closest
    -0.69
     JpaRepository
    -0.68
    TemporalType
    -0.63
    buzo
    -0.62
    曖昧さ回避
    -0.61
    tagHelper
    -0.61
     تضيفلها
    -0.60
    POSITIVE LOGITS
     enough
    0.96
     demais
    0.95
    enough
    0.90
     للغاية
    0.89
     ביותר
    0.81
    yet
    0.78
     ENOUGH
    0.77
     banget
    0.74
     genug
    0.73
     yet
    0.72
    Activations Density 0.021%

    No Known Activations