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. 22-GEMMASCOPE-RES-16K
    6. 6084
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly highlighting key figures and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numerical day of the month

    np_acts-logits-general · gemini-2.0-flash

    dates appearing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.94
     AssemblyTitle
    -0.85
     LoggerFactory
    -0.83
    Glej
    -0.82
     كومونز
    -0.81
    الإنجليزية
    -0.80
    InjectAttribute
    -0.79
     GenerationType
    -0.79
    DockStyle
    -0.75
    WriteTagHelper
    -0.73
    POSITIVE LOGITS
    0
    0.51
    3
    0.48
     Kapoor
    0.47
    8
    0.46
     Brasileiro
    0.46
     shearing
    0.46
    4
    0.46
    6
    0.45
    1
    0.44
     raider
    0.43
    Activations Density 0.137%

    No Known Activations