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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15078
    Prev
    Next
    INDEX
    Explanations

    terms related to specific chemical compounds or drugs

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

    "5" followed by a hyphen

    np_acts-logits-general · gemini-2.0-flash

    5- followed by specific words

    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
     betale
    -0.58
     CascadeType
    -0.54
    ArgsConstructor
    -0.53
     Dafür
    -0.50
    URLException
    -0.49
    AsUp
    -0.48
    CreateMap
    -0.48
    czaj
    -0.46
     Manns
    -0.46
    ActionCreators
    -0.46
    POSITIVE LOGITS
     BorderRadius
    0.72
    Hochspringen
    0.61
    CppMethod
    0.60
    Portály
    0.60
     AUSSI
    0.58
    Mord
    0.57
    InitVars
    0.56
     Khat
    0.55
    odb
    0.54
    AccessorTable
    0.53
    Activations Density 0.335%

    No Known Activations