© 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. 4-GEMMASCOPE-RES-16K
    11. 1717
    Prev
    Next
    INDEX
    Explanations

    formatting elements and commands related to document and figure management in LaTeX or similar markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Javadoc
    -0.67
     BorderRadius
    -0.63
    JspWriter
    -0.63
    AddTagHelper
    -0.58
     }</
    -0.58
    WriteTagHelper
    -0.56
     &&
    -0.54
    endaten
    -0.54
     tartalomajánló
    -0.54
     تانيه
    -0.53
    POSITIVE LOGITS
     Italijanski
    0.64
    tvguidetime
    0.62
     ucapnya
    0.58
    بوابة
    0.55
    出版年
    0.54
    ltä
    0.53
     Manoj
    0.52
     ulteriori
    0.52
     cucchiai
    0.52
    Huhu
    0.51
    Activations Density 0.131%

    No Known Activations