© 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. 22-GEMMASCOPE-RES-16K
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    references to mythical or legendary elements, particularly related to seals and gods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding a conjunction or punctuation

    np_acts-logits-general · gemini-2.0-flash

    method or problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.69
    awtextra
    -0.56
     rainbows
    -0.55
     propOrder
    -0.54
    principalColumn
    -0.52
     cherries
    -0.52
     sunsets
    -0.50
     assholes
    -0.50
    gameserver
    -0.50
     odkazy
    -0.50
    POSITIVE LOGITS
     thing
    0.68
     be
    0.64
     kind
    0.61
     everybody
    0.60
     person
    0.59
     place
    0.58
     possibility
    0.58
     oneself
    0.57
     again
    0.56
    kloped
    0.56
    Activations Density 0.263%

    No Known Activations