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. 4-GEMMASCOPE-RES-16K
    6. 370
    Prev
    Next
    INDEX
    Explanations

    references to Lego products and related constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.61
    pagestyle
    -0.56
    awaiter
    -0.55
    sunter
    -0.55
    ffilm
    -0.54
    beforeAll
    -0.54
     الدولى
    -0.53
    SwingConstants
    -0.53
    EREF
    -0.52
    czaj
    -0.51
    POSITIVE LOGITS
     Lego
    1.13
     LEGO
    1.12
     lego
    1.09
    LEGO
    1.06
    Lego
    1.01
     toy
    0.94
     toys
    0.86
    lego
    0.75
    Toy
    0.75
    toy
    0.75
    Activations Density 1.347%

    No Known Activations