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. 12-GEMMASCOPE-RES-16K
    6. 2388
    Prev
    Next
    INDEX
    Explanations

    elements of computer code related to errors and debugging information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.90
    الإنجليزية
    -0.77
    ConstraintMaker
    -0.77
    ValueStyle
    -0.74
    ResponseWriter
    -0.74
     surla
    -0.72
    EndContext
    -0.69
     تضيفلها
    -0.69
     المعيارى
    -0.68
    клопе
    -0.64
    POSITIVE LOGITS
    ualmente
    0.47
     рода
    0.45
    CustomerId
    0.44
     köny
    0.44
     đàn
    0.44
    argest
    0.43
    IVOS
    0.43
    geber
    0.42
    MessageOf
    0.42
     \|
    0.42
    Activations Density 1.014%

    No Known Activations