© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5375
    Prev
    Next
    INDEX
    Explanations

    negations and refutations of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weyl
    -0.89
     recto
    -0.89
     يتيمه
    -0.88
    DockStyle
    -0.87
     PTC
    -0.84
     homoto
    -0.83
     Sopho
    -0.81
     sorption
    -0.81
     fidu
    -0.81
     purpoſe
    -0.81
    POSITIVE LOGITS
     is
    1.29
     a
    1.03
     not
    0.98
     being
    0.97
     are
    0.96
     was
    0.94
     è
    0.93
     becoming
    0.91
     also
    0.91
     isn
    0.88
    Activations Density 0.118%

    No Known Activations