© 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. 9196
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically focusing on their birth information and associated details

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

    Opening parentheses, especially followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    parentheses

    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
     فريبيس
    -0.81
    :✨
    -0.77
     متعلقه
    -0.73
    ########.
    -0.64
    hyrchwyd
    -0.64
    RefNanny
    -0.63
     jLabel
    -0.60
     kaynağından
    -0.59
     Administrativna
    -0.57
     kasarigan
    -0.57
    POSITIVE LOGITS
     (
    0.49
     received
    0.46
    PointerException
    0.45
    cessive
    0.45
    cres
    0.44
    (
    0.44
    Received
    0.44
    cipar
    0.44
    nadequate
    0.44
     receivable
    0.43
    Activations Density 0.520%

    No Known Activations