Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29255
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and functions

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

    polynomials, functions, and number sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    KindOfClass
    -0.48
     "];
    -0.47
    offsetof
    -0.47
    әһ
    -0.46
    asteroide
    -0.46
     ſuo
    -0.45
    )]);
    -0.45
     tartalo
    -0.45
     fashiola
    -0.45
     Bone
    -0.44
    POSITIVE LOGITS
     AssemblyProduct
    0.63
    ьаж
    0.49
     otomatig
    0.47
    MessageTagHelper
    0.46
     Moscú
    0.44
    ViewFeatures
    0.43
    HasAnnotation
    0.42
     AssemblyCompany
    0.41
     NUKAT
    0.41
     EconPapers
    0.40
    Activations Density 0.005%

    No Known Activations