© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14352
    Prev
    Next
    INDEX
    Explanations

    the structure and formatting of pieces of text or data

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

    Followed by numbers or related to enumeration

    np_acts-logits-general · gemini-2.0-flash

    numbers and categories

    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
    Variants
    -0.63
    Traces
    -0.57
    Adapters
    -0.51
    Guides
    -0.50
    QueryParams
    -0.49
    Amounts
    -0.48
    Fragments
    -0.48
    cây
    -0.46
    Traits
    -0.46
    DATES
    -0.46
    POSITIVE LOGITS
     AssemblyCompany
    0.95
     betweenstory
    0.85
    BeginContext
    0.84
    出版年
    0.81
    MessageTagHelper
    0.81
    NOPQRST
    0.78
    XmlAccessorType
    0.77
     Offisielt
    0.76
    Portale
    0.69
    Према
    0.68
    Activations Density 1.652%

    No Known Activations