© 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. 1-GEMMASCOPE-RES-16K
    6. 9460
    Prev
    Next
    INDEX
    Explanations

    the term "super" in 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
     disambiguazione
    -0.88
    findpost
    -0.80
     AssemblyCompany
    -0.79
    Referències
    -0.78
    Geplaatst
    -0.76
    LEncoder
    -0.71
    RenderAtEndOf
    -0.71
     ModelExpression
    -0.68
    Portail
    -0.68
     praça
    -0.66
    POSITIVE LOGITS
     super
    5.10
    super
    4.58
     Super
    4.37
    Super
    4.29
     SUPER
    4.01
    SUPER
    3.78
     супер
    3.21
    超级
    3.00
     súper
    2.89
    uper
    2.85
    Activations Density 0.078%

    No Known Activations