© 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. 22-GEMMASCOPE-RES-16K
    11. 7214
    Prev
    Next
    INDEX
    Explanations

    the presence and structure of code blocks and conditional statements

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

    Code containing "if" statements

    np_acts-logits-general · gemini-2.0-flash

    conditional logic `if` statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.76
    parsedMessage
    -0.66
     nakalista
    -0.65
    TagHelpers
    -0.63
    ^(@)
    -0.63
     AssemblyTitle
    -0.61
     Italijanski
    -0.56
     Савезне
    -0.56
    malink
    -0.54
    vocable
    -0.53
    POSITIVE LOGITS
     if
    1.55
    if
    1.46
    If
    1.28
     If
    1.20
    IF
    1.00
     IF
    0.88
    如果
    0.87
     jika
    0.85
     dacă
    0.85
    Если
    0.83
    Activations Density 0.073%

    No Known Activations