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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 8429
    Prev
    Next
    INDEX
    Explanations

    C++ standard library function signatures and template usage patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C++ code containing "::" followed by a vector

    np_acts-logits-general · gemini-2.0-flash

    std::vector and std::string usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.69
     Namely
    -0.61
    onomía
    -0.57
    std
    -0.55
     FetchType
    -0.54
     Praha
    -0.53
     std
    -0.53
    glVertex
    -0.51
     estekak
    -0.51
     Ono
    -0.51
    POSITIVE LOGITS
     صوتيه
    0.60
     esternos
    0.59
    новниш
    0.58
     saites
    0.55
    agisse
    0.50
    Хьажоргаш
    0.49
    CompleteListener
    0.49
     '\\;'
    0.49
     calendriers
    0.48
    BagConstraints
    0.47
    Activations Density 0.075%

    No Known Activations