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. 19-GEMMASCOPE-RES-16K
    6. 11122
    Prev
    Next
    INDEX
    Explanations

    references to pastries and desserts, particularly cakes and baking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.63
     rurale
    -0.62
    },[])
    -0.61
    gesteld
    -0.61
     Bras
    -0.60
     Mantis
    -0.60
     AppCompat
    -0.60
    NgModule
    -0.58
    ropractor
    -0.58
    Gravel
    -0.57
    POSITIVE LOGITS
     cake
    1.85
     cakes
    1.68
     Cake
    1.57
    cake
    1.53
     Cakes
    1.45
    Cake
    1.44
     CAKE
    1.42
     baking
    1.30
     bake
    1.29
    Cakes
    1.25
    Activations Density 0.092%

    No Known Activations