Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9348
    Prev
    Next
    INDEX
    Explanations

    references to various types of oil, particularly olive oil

    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
    Referències
    -0.66
    FormTagHelper
    -0.59
     henkil
    -0.57
    urably
    -0.57
     ◄
    -0.55
    atific
    -0.55
     Herzegovina
    -0.54
    ñata
    -0.53
     createSprite
    -0.53
    terscotch
    -0.53
    POSITIVE LOGITS
     oil
    4.46
     Oil
    4.13
    Oil
    3.91
    oil
    3.87
     OIL
    3.74
     oils
    3.24
    OIL
    3.21
     Oils
    3.02
    油
    2.59
     Öl
    2.48
    Activations Density 0.072%

    No Known Activations