© 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. 25-GEMMASCOPE-RES-16K
    11. 12870
    Prev
    Next
    INDEX
    Explanations

    references to "Pokemon" and related fanfiction contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.71
    +:+
    -0.64
    ScopeManager
    -0.61
    PerformLayout
    -0.61
     defaultstate
    -0.59
     שוליים
    -0.58
    AnimationsModule
    -0.57
    IntoConstraints
    -0.57
     autorytatywna
    -0.57
    رشف
    -0.56
    POSITIVE LOGITS
     Pokemon
    1.20
     Pokémon
    1.19
     pokemon
    1.14
     Pok
    1.08
     Poke
    1.06
     trainer
    1.05
     trainers
    1.05
    Pokemon
    1.05
     Trainers
    1.04
    Pokémon
    1.03
    Activations Density 0.206%

    No Known Activations