© 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. 18-GEMMASCOPE-RES-16K
    11. 8346
    Prev
    Next
    INDEX
    Explanations

    HTML or XML-like tags and their content

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

    Markdown formatting and equation references

    np_acts-logits-general · gemini-2.0-flash

    references to tables and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     here
    -1.67
    here
    -1.35
     HERE
    -1.21
     Here
    -1.21
     aquí
    -1.19
     aqui
    -1.19
     ici
    -1.14
    Here
    -1.14
    HERE
    -1.13
     здесь
    -1.10
    POSITIVE LOGITS
    damento
    0.57
    parag
    0.52
     italic
    0.52
     paragraph
    0.52
    Sharper
    0.51
     footnotes
    0.51
     footnote
    0.49
    etas
    0.48
     paragraphs
    0.48
     Paragraph
    0.48
    Activations Density 0.560%

    No Known Activations