© 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. 18-GEMMASCOPE-RES-16K
    11. 4107
    Prev
    Next
    INDEX
    Explanations

    terms and identifiers related to medical and biological concepts

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

    ending in "en," "n," or "nn"

    np_acts-logits-general · gemini-2.0-flash

    German surnames ending in -en/-er

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tory
    -0.68
     qualitatively
    -0.68
    tent
    -0.67
    gies
    -0.67
    t
    -0.62
    dorp
    -0.61
    d
    -0.61
    tant
    -0.61
    tti
    -0.60
    trial
    -0.60
    POSITIVE LOGITS
    nen
    0.90
    ning
    0.87
    nnnn
    0.79
    en
    0.76
    na
    0.72
    nnn
    0.72
    nan
    0.70
    ghen
    0.69
    ned
    0.69
    nin
    0.68
    Activations Density 1.241%

    No Known Activations