© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7274
    Prev
    Next
    INDEX
    Explanations

    emotions and states of tranquility, particularly related to calmness

    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
    toMatchSnapshot
    -0.58
     seabed
    -0.55
    Jegyzetek
    -0.54
    übers
    -0.54
    Presentación
    -0.54
     INTERESAR
    -0.52
    aarrggbb
    -0.52
    IsContent
    -0.52
     تانيه
    -0.51
    cyj
    -0.51
    POSITIVE LOGITS
     nahilalakip
    0.80
    ute
    0.64
    ensement
    0.61
    nesses
    0.58
    ьаж
    0.58
    )$}
    0.57
     Testa
    0.57
     calm
    0.56
     []).
    0.56
     dull
    0.56
    Activations Density 0.081%

    No Known Activations