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. 23-GEMMASCOPE-RES-16K
    6. 12000
    Prev
    Next
    INDEX
    Explanations

    information related to procedures and formalities concerning examinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.64
     protoimpl
    -0.57
    matchCondition
    -0.51
    Odkazy
    -0.45
     attrs
    -0.45
     aceptas
    -0.43
    stopPropagation
    -0.42
    espé
    -0.41
    meliharaan
    -0.40
     január
    -0.39
    POSITIVE LOGITS
    Cleared
    0.74
     cleared
    0.70
    itorious
    0.69
     fresher
    0.67
     clearing
    0.66
     studies
    0.66
    cleared
    0.65
     topper
    0.65
     Pursu
    0.64
     toppers
    0.64
    Activations Density 0.107%

    No Known Activations