© 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. 3112
    Prev
    Next
    INDEX
    Explanations

    references to gaming communities and rules regarding player interactions

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

    online gaming servers and players

    np_acts-logits-general · gemini-2.0-flash

    player server PvP

    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
    AddTagHelper
    -0.75
     незавершена
    -0.72
     Meksiku
    -0.72
    Hochspringen
    -0.66
    GraphicsUnit
    -0.63
    UIControlState
    -0.63
    bootstrapcdn
    -0.60
    transQ
    -0.58
     Normdatei
    -0.58
     hidrá
    -0.57
    POSITIVE LOGITS
     server
    1.06
     player
    1.02
     players
    0.96
     Server
    0.91
     Player
    0.83
     servers
    0.82
     PvP
    0.82
    Player
    0.81
    player
    0.81
    Server
    0.80
    Activations Density 0.233%

    No Known Activations