© 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. 11080
    Prev
    Next
    INDEX
    Explanations

    questions and inquiry-related phrases or structures

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

    markers indicating questions in Q&A or numbered-list formats, including leading labels and punctuation that denote a question line

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

    question prompts or dialogue openings in interviews and Q&A sessions.

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

    question-answer format markers in interview and Q&A dialogue.

    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
    ientôt
    -0.57
    esgue
    -0.55
    ">
    -0.54
    #{
    -0.53
    moine
    -0.52
     instru
    -0.52
    felf
    -0.52
     {{$
    -0.52
    />";
    -0.51
     vig
    -0.51
    POSITIVE LOGITS
     propOrder
    0.80
     quelcon
    0.76
    ArgumentParser
    0.75
    LabelTagHelper
    0.73
    +#+#
    0.73
    Hozzáférés
    0.73
     why
    0.72
     how
    0.70
     quelconque
    0.69
    How
    0.68
    Activations Density 0.132%

    No Known Activations