© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15418
    Prev
    Next
    INDEX
    Explanations

    phrases or elements related to user authentication and social media interactions

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

    ending in "ski", "e", or "i"

    np_acts-logits-general · gemini-2.0-flash

    Slavic surnames

    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
    LookAnd
    -1.21
     CreateTagHelper
    -1.05
    BeginContext
    -1.05
    httphttps
    -1.00
    WebServlet
    -0.94
    IsContent
    -0.89
     الرياضيه
    -0.89
    thâu
    -0.88
    HasAnnotation
    -0.87
     utafitiHapana
    -0.86
    POSITIVE LOGITS
    se
    0.94
    ir
    0.80
    ς
    0.61
    м
    0.59
    m
    0.58
    ן
    0.57
    em
    0.56
    IR
    0.55
    ми
    0.55
    a
    0.54
    Activations Density 0.066%

    No Known Activations