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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11384
    Prev
    Next
    INDEX
    Explanations

    numerical data and references related to legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.94
    ValueStyle
    -0.85
    enumii
    -0.75
    Халык
    -0.69
    ⓧ
    -0.68
     насељу
    -0.64
    RegistryLite
    -0.61
    Gemeinden
    -0.60
    ParallelGroup
    -0.60
    جوايز
    -0.59
    POSITIVE LOGITS
    ódó
    0.57
    getActiveSheet
    0.55
    rungsseite
    0.54
    jsonwebtoken
    0.54
    сюда
    0.53
     carottes
    0.52
    providedIn
    0.52
     venons
    0.51
    ходим
    0.50
    팎
    0.50
    Activations Density 0.861%

    No Known Activations