© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7914
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a personal connection to experiences and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transférez
    -0.64
     tadi
    -0.60
    今後
    -0.58
     originally
    -0.58
    migrationBuilder
    -0.57
     forse
    -0.57
    GEBURTSDATUM
    -0.57
    vatar
    -0.56
     originalmente
    -0.55
     protoimpl
    -0.55
    POSITIVE LOGITS
     whenever
    1.09
    Either
    1.02
     either
    1.00
    Whenever
    0.97
    either
    0.97
     Whenever
    0.97
     Either
    0.94
    whenever
    0.93
     whichever
    0.92
     câte
    0.91
    Activations Density 0.298%

    No Known Activations