© 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. 4345
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical data and functions

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

    Programming syntax and string manipulation

    np_acts-logits-general · gemini-2.0-flash

    code syntaxprogrammatic syntax

    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
     referenties
    -0.86
     Paglinawan
    -0.83
    setVerticalGroup
    -0.75
    ագրություններ
    -0.74
    rungsseite
    -0.70
     '\\;'
    -0.69
    TagMode
    -0.68
    ItemBackground
    -0.68
     defaultstate
    -0.68
    Personendaten
    -0.67
    POSITIVE LOGITS
    ​—
    0.53
    ">/
    0.52
     IBRARY
    0.51
     Eles
    0.50
    -​
    0.48
    »։
    0.47
    viewDid
    0.47
     Glaube
    0.47
    zką
    0.46
    quele
    0.46
    Activations Density 0.597%

    No Known Activations