© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8376
    Prev
    Next
    INDEX
    Explanations

    quoted strings and special characters in a structured document

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

    opening quotation marks in structured data or code strings.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.67
     وتسجيلات
    -0.66
    хьтан
    -0.66
     Signalez
    -0.65
    SourceChecksum
    -0.65
    AddTagHelper
    -0.63
    ValueStyle
    -0.60
    StructEnd
    -0.57
     للاسماء
    -0.56
    InjectAttribute
    -0.54
    POSITIVE LOGITS
    "=>"
    0.77
    ()"
    0.76
    ?"
    0.76
    !"
    0.75
    .."
    0.75
     ..."
    0.75
    ","
    0.74
    ("
    0.71
    !!"
    0.69
    ."
    0.68
    Activations Density 0.597%

    No Known Activations