© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 1876
    Prev
    Next
    INDEX
    Explanations

    references to playing or engaging in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.85
    gnore
    -0.84
     Hutchinson
    -0.84
    LikeLike
    -0.83
    enment
    -0.82
    ])));
    -0.81
     مرئيه
    -0.80
     maternelle
    -0.79
     GIPHY
    -0.79
    otonin
    -0.77
    POSITIVE LOGITS
     play
    1.65
     PLAY
    1.51
    PLAY
    1.47
     Play
    1.42
    play
    1.38
    Play
    1.38
     played
    1.36
     plays
    1.35
    plays
    1.28
     Plays
    1.25
    Activations Density 0.062%

    No Known Activations