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. 20-GEMMASCOPE-RES-16K
    6. 15741
    Prev
    Next
    INDEX
    Explanations

    markers signaling the beginning of a new section or document

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

    Code, math, or symbol-related text

    np_acts-logits-general · gemini-2.0-flash

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.88
     समीक्षाओं
    -0.82
    richTextPanel
    -0.77
    ⓧ
    -0.76
    BeginContext
    -0.70
    MessageTagHelper
    -0.69
    extAlignment
    -0.68
    发表于
    -0.68
     oprot
    -0.67
    providedIn
    -0.66
    POSITIVE LOGITS
    Linq
    1.69
    Collectors
    0.51
    enumerable
    0.45
    яви
    0.45
    Silen
    0.45
     LIN
    0.43
     الوطنيه
    0.43
     Hermans
    0.43
    ниципа
    0.42
    NewGuid
    0.41
    Activations Density 0.018%

    No Known Activations