© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 4086
    Prev
    Next
    INDEX
    Explanations

    phrases and questions related to personal reflection and experiences

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

    specific characters or sequences

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

    the neuron detects superlative/extreme degree words and related question contexts (e.g., "most", "highest", "most unusual" in questions).

    oai_token-act-pair · gpt-5-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.73
    MigrationBuilder
    -0.68
     الحره
    -0.67
    脚注の使い方
    -0.61
    __(/*!
    -0.57
     consultato
    -0.56
    principalColumn
    -0.56
     EconPapers
    -0.53
    ConstraintMaker
    -0.52
     دیکھیے
    -0.51
    POSITIVE LOGITS
     Exacts
    0.41
    uParam
    0.38
    eniendo
    0.37
     McEl
    0.37
    cat
    0.37
    quila
    0.37
    ناك
    0.36
     Giles
    0.36
    kat
    0.36
     Marques
    0.36
    Activations Density 0.302%

    No Known Activations