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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6833
    Prev
    Next
    INDEX
    Explanations

    specific terms related to user account management and password operations

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

    Confirmation, password, or account activation

    np_acts-logits-general · gemini-2.0-flash

    account confirmation and password reset

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    uncios
    -0.54
    出版年
    -0.51
    databind
    -0.50
     EconPapers
    -0.49
     reacción
    -0.48
     respiración
    -0.46
     Infór
    -0.46
     scolaires
    -0.45
     Economía
    -0.45
     Constitucional
    -0.45
    POSITIVE LOGITS
    Apa
    0.40
     فريبيس
    0.39
     FetchType
    0.38
     Apa
    0.38
    Personensuche
    0.36
    ColumnHeaders
    0.36
     rings
    0.35
     mid
    0.35
     Fos
    0.35
     Rescue
    0.34
    Activations Density 0.115%

    No Known Activations