© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7454
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "loop" and related circular or cyclical concepts

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

    words and phrases related to circular motion, including "loop", "circling", and "around".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <strong>
    -0.42
     a
    -0.41
    s
    -0.38
    t
    -0.38
     and
    -0.37
    MAN
    -0.37
    a
    -0.36
     New
    -0.36
     white
    -0.35
     Faculty
    -0.35
    POSITIVE LOGITS
     LOOP
    1.09
     CIRCLE
    1.04
     loop
    1.03
     Loop
    0.97
    IsMutable
    0.96
    Loop
    0.95
     looped
    0.95
    verwijspagina
    0.95
    ImageContext
    0.94
    loop
    0.93
    Activations Density 0.137%

    No Known Activations