Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6001
    Prev
    Next
    INDEX
    Explanations

    key terms related to error measurement and optimization in statistical models and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.74
     يتيمه
    -0.70
    ########.
    -0.66
     <>",
    -0.65
    paux
    -0.64
    ItemBackground
    -0.59
     autorytatywna
    -0.57
    anadium
    -0.54
     թվական
    -0.53
     BeautifulSoup
    -0.53
    POSITIVE LOGITS
     distance
    1.29
     Distance
    1.16
    distance
    1.10
    Distance
    1.10
     distances
    1.07
     Distances
    0.95
     DISTANCE
    0.94
     distancia
    0.91
    距離
    0.89
    DISTANCE
    0.87
    Activations Density 0.912%

    No Known Activations