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. 11-GEMMASCOPE-RES-16K
    6. 7306
    Prev
    Next
    INDEX
    Explanations

    information related to charitable actions and social service initiatives

    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
     gesteld
    -0.55
     классе
    -0.55
    KELEY
    -0.55
     artigos
    -0.55
     Kelas
    -0.52
     класса
    -0.52
    entrion
    -0.51
     nyug
    -0.50
     gainera
    -0.49
    PONENT
    -0.49
    POSITIVE LOGITS
     Majefty
    0.69
    CppMethod
    0.67
    PhysRevLett
    0.57
    AntiForgeryToken
    0.57
     Diſ
    0.57
    CloseOperation
    0.57
     Billboard
    0.56
     Jove
    0.56
    @[+][
    0.56
     whofe
    0.56
    Activations Density 0.127%

    No Known Activations