Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 119235
    Prev
    Next
    INDEX
    Explanations

    the repeated presence of the token "Qu"

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

    words starting with Qu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     łóż
    -0.48
     כול
    -0.48
    ggior
    -0.45
    sterious
    -0.44
     Morelos
    -0.44
    elus
    -0.43
    []>
    -0.43
    marie
    -0.43
    <h3>
    -0.43
    ekš
    -0.42
    POSITIVE LOGITS
     Qu
    1.89
    Qu
    1.75
     QU
    1.20
    Quic
    0.83
     qu
    0.78
    Quotation
    0.78
     Quo
    0.77
    QU
    0.74
     Quake
    0.72
     quenching
    0.71
    Activations Density 0.004%

    No Known Activations