© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 102416
    Prev
    Next
    INDEX
    Explanations

    questions and their responses

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    answers

    np_acts-logits-general · gemini-2.5-flash-lite

    Sentences or tokens marking question-and-answer structure (Q/A labels and answer text).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    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
    Negative Logits
    KommentareTeilen
    -0.49
    tagPool
    -0.40
    CppMethod
    -0.40
    )++;
    -0.40
    ThroughAttribute
    -0.39
    adpleegd
    -0.37
    blit
    -0.36
    emang
    -0.36
    =<?
    -0.35
     hood
    -0.34
    POSITIVE LOGITS
     answers
    1.30
     answer
    1.30
     answered
    1.16
    answer
    1.16
     Answers
    1.09
     answering
    1.09
     Answer
    1.08
     Antwort
    1.05
    answers
    1.02
    Answer
    1.01
    Activations Density 0.498%

    No Known Activations