© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7916
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to programming and computing

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

    Code or data context markers

    np_acts-logits-general · gemini-2.0-flash

    with followed by a noun

    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
    Location
    -1.29
     location
    -1.25
     Location
    -1.21
     LOCATION
    -1.15
     locations
    -1.13
    LOCATION
    -1.12
    location
    -1.12
    Locations
    -1.08
     ubicación
    -1.07
     Locations
    -1.06
    POSITIVE LOGITS
    ništvo
    0.56
     phone
    0.55
     Quaternion
    0.54
    ẢN
    0.53
    EndProject
    0.52
     Fest
    0.52
     Phone
    0.51
     архивлан
    0.51
    mazoo
    0.50
    zini
    0.50
    Activations Density 0.192%

    No Known Activations