© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13483
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases and expressions of questioning

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

    language that poses or introduces a question—signals of inquiry such as “raising/asking/wondering” constructions and nearby question punctuation and quotes.

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    questions or expressions of inquiry.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    questions and interrogative expressions, particularly detecting the word "question," verbs like "ask" and "wonder," question marks, and interrogative words.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.75
     للمعارف
    -0.71
    fortawesome
    -0.61
    Descrizione
    -0.59
     clearColor
    -0.59
    borderSide
    -0.59
     noqa
    -0.57
     للاسماء
    -0.56
    Xna
    -0.56
    ThroughAttribute
    -0.55
    POSITIVE LOGITS
     questions
    1.43
     question
    1.41
     Questions
    1.25
     QUESTIONS
    1.23
    question
    1.22
     Question
    1.20
    Questions
    1.18
    questions
    1.15
     QUESTION
    1.09
    QUESTIONS
    1.09
    Activations Density 0.307%

    No Known Activations