© 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. 0-GEMMASCOPE-RES-16K
    11. 9493
    Prev
    Next
    INDEX
    Explanations

    affirmative or negative statements about conditions or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rosse
    -0.58
    空的
    -0.55
     garnet
    -0.54
     terdekat
    -0.54
    alva
    -0.51
     hinted
    -0.51
     oubli
    -0.51
    עוד
    -0.51
     LIRE
    -0.51
    ılır
    -0.51
    POSITIVE LOGITS
    ValueStyle
    1.01
     siendo
    1.00
     being
    1.00
    protoimpl
    0.99
     é
    0.98
    Being
    0.96
     Being
    0.96
    GEBURTSDATUM
    0.94
     fue
    0.92
    being
    0.91
    Activations Density 0.097%

    No Known Activations