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. 11-GEMMASCOPE-RES-16K
    6. 14045
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageField
    -0.91
    Хьажоргаш
    -0.85
    linger
    -0.83
    assium
    -0.81
    ########.
    -0.78
     Egl
    -0.77
     Irina
    -0.75
    e
    -0.75
    JNIEnv
    -0.74
    makeConstraints
    -0.73
    POSITIVE LOGITS
     dispatch
    0.91
    =-=-=-=-
    0.80
    dispatch
    0.80
     Tribune
    0.79
     Dispatch
    0.77
     disponibilités
    0.74
     UserService
    0.73
     useDispatch
    0.73
    Dispatch
    0.73
     Brew
    0.72
    Activations Density 0.197%

    No Known Activations