© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8370
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific narrative structures in the text

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    labels, headings, and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.38
     Chwiliwch
    -0.38
     perfección
    -0.38
    })`
    -0.36
    CrossRef
    -0.34
    suitable
    -0.33
     dinámica
    -0.33
     habitaciones
    -0.33
     talentos
    -0.33
     preferencias
    -0.32
    POSITIVE LOGITS
     Shortly
    0.56
     propOrder
    0.55
    Shortly
    0.54
     vooraf
    0.53
    labelledby
    0.52
    newtheorem
    0.51
    Hist
    0.51
     preceded
    0.50
    ismet
    0.50
    djangoproject
    0.50
    Activations Density 0.526%

    No Known Activations