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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 15182
    Prev
    Next
    INDEX
    Explanations

    content related to video game mechanics and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cantando
    -0.64
     jScrollPane
    -0.57
     bailando
    -0.56
    AddTagHelper
    -0.54
     Jagger
    -0.53
    Poem
    -0.53
    esModule
    -0.52
    NamedQuery
    -0.51
    complexType
    -0.51
    Архівовано
    -0.51
    POSITIVE LOGITS
     gameplay
    1.70
     game
    1.58
     playable
    1.42
     games
    1.31
     Gameplay
    1.28
    game
    1.25
     player
    1.22
     Game
    1.21
     players
    1.21
     multiplayer
    1.16
    Activations Density 0.758%

    No Known Activations