© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 61095
    Prev
    Next
    INDEX
    Explanations

    occurrences of the "foreach" and "each" programming constructs in the text

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

    foreach loop syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⟬
    -0.49
    Ripple
    -0.44
     Milla
    -0.44
     LCCN
    -0.42
    servable
    -0.42
     rospy
    -0.42
     altitude
    -0.42
    /**
    -0.41
     ujednoznacz
    -0.40
    OrNil
    -0.40
    POSITIVE LOGITS
    foreach
    1.84
     foreach
    1.34
    forEach
    0.77
    ForEach
    0.71
    Among
    0.69
     AMONG
    0.69
    among
    0.68
     Among
    0.67
     among
    0.65
     amongst
    0.62
    Activations Density 0.001%

    No Known Activations