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. 21-GEMMASCOPE-RES-16K
    6. 7239
    Prev
    Next
    INDEX
    Explanations

    references to personal ownership and individual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    ViewFeatures
    -0.68
    Referències
    -0.58
    Referințe
    -0.54
     Roskov
    -0.52
     inimes
    -0.51
     players
    -0.51
    MockBean
    -0.50
     SafeMath
    -0.50
    UserScript
    -0.49
    providedIn
    -0.49
    POSITIVE LOGITS
     Photocase
    0.84
     request
    0.68
     choice
    0.67
     complaint
    0.67
    rungsseite
    0.65
    TagMode
    0.65
     purchase
    0.64
     rights
    0.63
     account
    0.60
     purchases
    0.60
    Activations Density 0.246%

    No Known Activations