© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10920
    Prev
    Next
    INDEX
    Explanations

    programming syntax, such as function definitions and variable declarations

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

    Programming code or math expressions

    np_acts-logits-general · gemini-2.0-flash

    code snippets and symbols like `**`

    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
    DockStyle
    -0.73
    AndEndTag
    -0.72
    rungsseite
    -0.72
     autorytatywna
    -0.68
    IsMutable
    -0.67
    はじめに
    -0.67
    tanleria
    -0.66
    Rujuakan
    -0.66
    GIVEREF
    -0.66
    
    -0.65
    POSITIVE LOGITS
    STAND
    0.51
    DllImport
    0.48
    ghijklmnop
    0.48
    shub
    0.46
    Mozilla
    0.45
     tương
    0.44
     civil
    0.44
    stam
    0.43
     στε
    0.43
     standen
    0.43
    Activations Density 0.413%

    No Known Activations