© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56531
    Prev
    Next
    INDEX
    Explanations

    references to programming models and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.89
    WindowConstants
    -0.73
    FormTagHelper
    -0.72
     kaarangay
    -0.72
    AndEndTag
    -0.71
    QtWidgets
    -0.70
    SBATCH
    -0.70
    RTEX
    -0.70
     transfieras
    -0.69
     Taktlose
    -0.69
    POSITIVE LOGITS
     Model
    0.60
    CreateModel
    0.54
     model
    0.51
     MODEL
    0.51
    Model
    0.51
    BASEPATH
    0.50
    JdbcTemplate
    0.49
    MODEL
    0.49
     especializados
    0.48
    ================
    0.48
    Activations Density 0.001%

    No Known Activations