Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4047
    Prev
    Next
    INDEX
    Explanations

    words related to gaming and game mechanics

    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
     الحره
    -0.59
    tableFuture
    -0.58
    ILayout
    -0.55
     QtWidgets
    -0.54
     CreateTagHelper
    -0.54
    OrBuilder
    -0.53
     &___
    -0.52
     nakalista
    -0.52
     вікі
    -0.51
    __["
    -0.51
    POSITIVE LOGITS
     play
    3.20
    play
    2.73
     playing
    2.73
     plays
    2.68
     played
    2.67
     Play
    2.53
    Play
    2.51
     PLAY
    2.45
    plays
    2.31
    playing
    2.30
    Activations Density 0.327%

    No Known Activations