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. 1-GEMMASCOPE-RES-16K
    6. 5970
    Prev
    Next
    INDEX
    Explanations

    references to the center or middle point of various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.77
     فريبيس
    -0.76
     Administrativna
    -0.74
    TestingModule
    -0.64
    expandindo
    -0.62
     Paglinawan
    -0.58
     Италијани
    -0.58
     defStyleAttr
    -0.57
    ExecuteReader
    -0.57
    IsMutable
    -0.57
    POSITIVE LOGITS
     centre
    2.47
     center
    2.30
    centre
    1.79
     centres
    1.78
     centers
    1.57
     centro
    1.49
    center
    1.34
     centrum
    1.26
     центре
    1.25
    中心
    1.22
    Activations Density 0.125%

    No Known Activations