© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9393
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of uncertainty in relation to outcomes or behaviors

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     tartalomajánló
    -0.73
    LEncoder
    -0.72
    PerformLayout
    -0.69
    AccessorTable
    -0.66
     bezeichneter
    -0.64
     дописавши
    -0.64
     Bourgoin
    -0.62
    WireFormat
    -0.58
    exitRule
    -0.57
     ]}
    -0.56
    POSITIVE LOGITS
    usepackage
    0.50
    HomeAsUpEnabled
    0.49
    indic
    0.47
    ByVersion
    0.45
     BrowserModule
    0.45
    нд
    0.44
    ORM
    0.44
    InSection
    0.43
    IContainer
    0.43
    UTIVE
    0.42
    Activations Density 0.393%

    No Known Activations