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. 22-GEMMASCOPE-RES-16K
    6. 11142
    Prev
    Next
    INDEX
    Explanations

    references to methods and functionalities associated with the MediaPlayer in programming contexts

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

    "Play" or "Player" related terms and contexts

    np_acts-logits-general · gemini-2.0-flash

    player is playing

    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
     lò
    -0.46
     impresa
    -0.44
    gence
    -0.43
     בני
    -0.41
    改正
    -0.40
    ành
    -0.40
    CreateTable
    -0.40
    抬头
    -0.39
    hobo
    -0.38
    mamış
    -0.38
    POSITIVE LOGITS
     player
    1.62
     play
    1.55
     playing
    1.53
     Player
    1.43
    player
    1.42
     Playing
    1.41
    play
    1.40
     playback
    1.40
    Play
    1.39
     Play
    1.38
    Activations Density 0.364%

    No Known Activations