© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 12920
    Prev
    Next
    INDEX
    Explanations

    complex scientific terms and equations related to spin, thermal properties, and quantum physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.69
    KommentareTeilen
    -0.69
    findpost
    -0.69
     Мексичка
    -0.60
    BeginContext
    -0.59
    ImageContext
    -0.59
    gameserver
    -0.59
    Obrázky
    -0.56
    hrten
    -0.55
    MLLoader
    -0.54
    POSITIVE LOGITS
     touristique
    0.57
     chrétien
    0.48
     olympique
    0.46
     bambou
    0.46
    anis
    0.46
     chaussures
    0.44
     baño
    0.43
     pierres
    0.43
    zono
    0.41
     peinados
    0.41
    Activations Density 3.670%

    No Known Activations