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. 61780
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their various forms in multiple languages

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

    jalapeño, HLA allele, network

    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
     resourceCulture
    -0.57
    Personendaten
    -0.54
    uxxxx
    -0.53
    dafx
    -0.49
     nahilalakip
    -0.48
     &___
    -0.48
     Walkover
    -0.46
    Aholisi
    -0.45
    istock
    -0.43
     препратки
    -0.43
    POSITIVE LOGITS
    InputBorder
    0.54
     estekak
    0.53
     pinulongan
    0.51
     iconLine
    0.47
    ApplicationTests
    0.43
    spesies
    0.43
    DrawerToggle
    0.43
    chowa
    0.42
    IntoConstraints
    0.41
    DialogFragment
    0.40
    Activations Density 0.287%

    No Known Activations