© 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. 20-GEMMASCOPE-RES-131K
    11. 17407
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their forms in the text

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

    pronoun starts or 'let'

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

    sentence-start tokens—short capitalized words (like I, You, It, Let, or single-letter labels) that begin a response or utterance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ngoại
    -0.51
    </tfoot>
    -0.49
     ExecuteAsync
    -0.42
    setVerticalGroup
    -0.42
    oa̍t
    -0.42
     Reverb
    -0.41
     progressive
    -0.40
    出版年
    -0.40
    StructEnd
    -0.40
     report
    -0.39
    POSITIVE LOGITS
     utafitiHapana
    0.48
    Personendaten
    0.44
    findpost
    0.41
    InputTagHelper
    0.41
    ANTLR
    0.40
     otomatig
    0.38
    onViewCreated
    0.36
     initComponents
    0.35
     TextAppearance
    0.35
    Fields
    0.34
    Activations Density 0.005%

    No Known Activations