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

    Neuronpedia

    APICircuit 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. 11-GEMMASCOPE-RES-16K
    6. 5640
    Prev
    Next
    INDEX
    Explanations

    flavor descriptors and characteristics of food or beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agar
    -0.49
     bloß
    -0.48
    除
    -0.47
    منت
    -0.47
    スメ
    -0.45
     المنت
    -0.45
    Cubit
    -0.44
     jedin
    -0.43
    meln
    -0.43
                                   
    -0.43
    POSITIVE LOGITS
    }$​
    0.66
    كونات
    0.60
    guenos
    0.60
     myſelf
    0.58
    ENEFITS
    0.58
    Попис
    0.57
    glise
    0.57
    ÚBL
    0.55
     kautta
    0.55
     ſte
    0.54
    Activations Density 0.024%

    No Known Activations