© 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. 14881
    Prev
    Next
    INDEX
    Explanations

    elements of structured programming syntax and data structures commonly found in code

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

    Code, math, or special characters

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and symbols

    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
    存于互联网档案馆
    -1.10
    InputBorder
    -1.10
    enumi
    -1.09
    NUMX
    -1.08
     GIPHY
    -1.06
     كومونز
    -1.06
    BufferException
    -1.05
     iſt
    -1.03
    AnimationsModule
    -1.00
     arşivlendi
    -1.00
    POSITIVE LOGITS
     (
    1.16
     
    1.16
    ,
    1.05
     "
    1.04
     a
    0.94
     -
    0.92
    .
    0.91
    ↵↵
    0.90
    ↵
    0.89
    :
    0.88
    Activations Density 2.750%

    No Known Activations