© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8311
    Prev
    Next
    INDEX
    Explanations

    elements related to API functionality, particularly regarding operations on virtual private network (VPN) sites

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

    Text related to API responses and schemas

    np_acts-logits-general · gemini-2.0-flash

    sites and tags response DTOs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sağ
    -0.38
     virgen
    -0.38
     Mundial
    -0.35
    Clik
    -0.34
     pää
    -0.34
    leitung
    -0.34
    Cách
    -0.34
    ErrorHandler
    -0.33
    MethodName
    -0.33
    SaveChangesAsync
    -0.33
    POSITIVE LOGITS
     response
    0.97
    MemoryWarning
    0.96
     responses
    0.86
    response
    0.86
     Response
    0.84
    Dto
    0.84
     réponse
    0.83
     dto
    0.83
    DTO
    0.83
    ResponseDto
    0.82
    Activations Density 0.394%

    No Known Activations