© 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. 38103
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity, particularly involving 'at least one' and possessive forms

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

    quantifier + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     незавершена
    -0.60
    ipheral
    -0.54
    Referências
    -0.52
     chi̍t
    -0.51
     invitaciones
    -0.50
    สาย
    -0.48
    ſche
    -0.48
    calça
    -0.48
    مراجع
    -0.47
     člověk
    -0.47
    POSITIVE LOGITS
    self
    0.39
    期刊论文
    0.39
    minecraftforge
    0.38
     pick
    0.37
     Landlord
    0.36
     maga
    0.36
    hood
    0.35
     len
    0.35
    RSpec
    0.35
    ]]]
    0.35
    Activations Density 0.188%

    No Known Activations