© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1409
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotations and periods

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

    Punctuation mark at the end of a quote

    np_acts-logits-general · gemini-2.0-flash

    closing quotation marks and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    '>
    -0.81
    पया
    -0.65
    -
    -0.65
     >
    -0.65
     getIndex
    -0.64
    出版年
    -0.63
    ++
    -0.62
     Administrativna
    -0.62
     Gibb
    -0.61
     ]
    -0.61
    POSITIVE LOGITS
    .”
    0.81
    ."
    0.80
    ?”
    0.65
    ,”
    0.63
    。”
    0.63
    ?"
    0.61
    …”
    0.61
    ,"
    0.60
    ."""
    0.57
    .’”
    0.56
    Activations Density 0.182%

    No Known Activations