© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 8727
    Prev
    Next
    INDEX
    Explanations

    words related to loss or deprivation

    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
     Koy
    -0.49
    mbo
    -0.48
     stanovnika
    -0.48
     sempurna
    -0.47
    ubation
    -0.47
    جستارهای
    -0.47
     isolé
    -0.46
     manuale
    -0.46
     Điều
    -0.45
     perfeita
    -0.45
    POSITIVE LOGITS
     unknownFields
    0.61
    tinyos
    0.57
    ency
    0.54
     Dolom
    0.51
    ents
    0.49
     Blanchard
    0.49
    entia
    0.49
    ently
    0.49
    itaan
    0.48
    MENAFN
    0.48
    Activations Density 0.207%

    No Known Activations