© 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. 18-GEMMASCOPE-RES-16K
    11. 10323
    Prev
    Next
    INDEX
    Explanations

    references to user involvement and feedback in creative or informal contexts

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

    the prefix "Q:" in questions

    np_acts-logits-general · gemini-2.0-flash

    Pokémon evolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.68
    parsedMessage
    -0.61
     EconPapers
    -0.58
    UpInside
    -0.57
     defaultstate
    -0.54
     --}}
    -0.53
    DECREF
    -0.53
    出版年
    -0.52
     InputDecoration
    -0.51
    AndroidJUnit
    -0.51
    POSITIVE LOGITS
     Pokémon
    1.09
     Pokemon
    1.00
    Pokémon
    0.99
     pokemon
    0.95
    Pokemon
    0.90
     Poke
    0.78
     Pok
    0.77
    pokemon
    0.76
     pokémon
    0.74
     trainer
    0.74
    Activations Density 0.114%

    No Known Activations