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. 1809
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and components related to user interface elements and data management within various programming frameworks

    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
    dicionado
    -0.59
    jarat
    -0.49
    GEBURTS
    -0.48
    setBounds
    -0.48
    OGND
    -0.47
     الاطلاع
    -0.46
     Ahu
    -0.45
    mapsto
    -0.45
    Rptr
    -0.45
    erequisites
    -0.44
    POSITIVE LOGITS
     MonoBehaviour
    1.39
     StatelessWidget
    1.14
    rungsseite
    1.10
     StatefulWidget
    1.04
     ControllerBase
    0.99
    WithIOException
    0.98
    ReusableCell
    0.94
    UserScript
    0.89
    يميديا
    0.86
    AsUp
    0.82
    Activations Density 0.085%

    No Known Activations