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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 40836
    Prev
    Next
    INDEX
    Explanations

    phrases related to tax evasion and financial misconduct

    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
     tuning
    -0.34
     cutting
    -0.33
     Tuning
    -0.32
    EUROPA
    -0.32
     Cutting
    -0.32
     paddles
    -0.30
     load
    -0.30
     hoes
    -0.30
     GL
    -0.29
    InitVars
    -0.29
    POSITIVE LOGITS
    RTDA
    0.63
     ویکی‌پدی
    0.56
    تقاوى
    0.56
     nakalista
    0.54
    <>());
    0.53
    RegressionTest
    0.53
    LookAnd
    0.53
     NSCoder
    0.53
    #+#
    0.52
    MigrationBuilder
    0.52
    Activations Density 0.038%

    No Known Activations