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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 68745
    Prev
    Next
    INDEX
    Explanations

    references to software components and their functionalities

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

    Firebase Firestore

    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
     esternos
    -0.55
     nahilalakip
    -0.52
    VersionUID
    -0.50
     चीज़ों
    -0.49
    LookAnd
    -0.49
    脚注の使い方
    -0.48
    FormTagHelper
    -0.48
     PopupWindow
    -0.47
    ьажоргаш
    -0.47
    ंदीखरीदारी
    -0.47
    POSITIVE LOGITS
     Fire
    0.82
    Fire
    0.76
    fire
    0.71
     fire
    0.71
     FIRE
    0.63
    FIRE
    0.57
    Firestore
    0.55
    ofire
    0.54
     Feuer
    0.52
     Firebase
    0.52
    Activations Density 0.001%

    No Known Activations