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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103219
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain significant formatting or whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    webElementGuid
    -0.52
    indd
    -0.48
     NavController
    -0.47
    Personendaten
    -0.47
    bolista
    -0.46
    ⎦
    -0.45
     szóci
    -0.45
     оригіналу
    -0.44
     الاطلاع
    -0.43
     tslint
    -0.43
    POSITIVE LOGITS
     Histórico
    0.37
    Story
    0.35
    Technology
    0.35
     journée
    0.35
    RegressionTest
    0.34
     teórico
    0.34
    Evidence
    0.34
     betweenstory
    0.34
    Firstly
    0.34
    Dimension
    0.33
    Activations Density 0.010%

    No Known Activations