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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6219
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.53
    evos
    -0.52
     estadounid
    -0.52
     lisäksi
    -0.51
     themſelves
    -0.51
     conmigo
    -0.50
     policiales
    -0.50
     miniaturka
    -0.49
     للمعارف
    -0.48
     cinese
    -0.48
    POSITIVE LOGITS
    хьтан
    0.52
     Artic
    0.46
    MENAFN
    0.42
     sav
    0.41
     aud
    0.40
    Thir
    0.40
     Shoot
    0.40
     bas
    0.39
     shir
    0.39
     acc
    0.39
    Activations Density 0.828%

    No Known Activations