© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10473
    Prev
    Next
    INDEX
    Explanations

    code structures related to loops and iteration in programming

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

    Code context: loops and array indexing

    np_acts-logits-general · gemini-2.0-flash

    for loop constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.68
     étoient
    -0.60
     müſſen
    -0.59
     MainAxisSize
    -0.57
     ſelbſt
    -0.57
    parsedMessage
    -0.57
    delivered
    -0.55
    enablog
    -0.55
     avoient
    -0.54
     ſehr
    -0.54
    POSITIVE LOGITS
     i
    0.76
     I
    0.60
     j
    0.45
     loop
    0.41
    i
    0.39
     ii
    0.38
     x
    0.37
     y
    0.33
     loops
    0.32
     finger
    0.32
    Activations Density 0.127%

    No Known Activations