© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38512
    Prev
    Next
    INDEX
    Explanations

    words and suffixes related to queries or questioning

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

    que or ique suffix

    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
    MLLoader
    -0.57
    GOTREF
    -0.56
     adota
    -0.47
     ainfi
    -0.46
    miller
    -0.44
     étrangère
    -0.43
     fVar
    -0.43
    need
    -0.43
    adopted
    -0.43
     enfance
    -0.42
    POSITIVE LOGITS
    que
    2.20
    QUE
    1.66
    ques
    1.63
    QUES
    1.31
    IQUE
    1.25
    ique
    1.21
    Que
    1.09
     QUE
    0.99
    rique
    0.96
    quef
    0.96
    Activations Density 0.011%

    No Known Activations