© 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. 16-GEMMASCOPE-RES-16K
    6. 1924
    Prev
    Next
    INDEX
    Explanations

    events related to memorial services and celebrations of life

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

    Follows a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    following punctuation, abbreviations, or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.86
    CompoundButton
    -0.69
    stateProvider
    -0.64
    sitis
    -0.57
     pese
    -0.57
     sven
    -0.56
    éal
    -0.56
    numerusform
    -0.56
     едва
    -0.55
    CppCodeGen
    -0.54
    POSITIVE LOGITS
     privately
    0.50
    ModelBuilder
    0.47
     loving
    0.46
     service
    0.46
    IsContent
    0.45
    ợt
    0.45
     uzav
    0.45
    jelent
    0.45
    doğan
    0.44
    Celebration
    0.44
    Activations Density 0.012%

    No Known Activations