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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5460
    Prev
    Next
    INDEX
    Explanations

    terms related to airbags and their components in restraint systems

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

    airbag restraint cushions

    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
    entierung
    -0.38
     kebun
    -0.37
    ナブル
    -0.36
     Tiefe
    -0.35
    atyw
    -0.34
    NOPQRST
    -0.33
     đọc
    -0.33
    本事
    -0.33
     colectiva
    -0.32
    \":\"
    -0.31
    POSITIVE LOGITS
     airbag
    1.03
     airbags
    0.94
    Personensuche
    0.69
    posedge
    0.65
     deſt
    0.63
     ویکی‌پدی
    0.60
    jsonwebtoken
    0.60
     faſt
    0.60
    يكب
    0.59
     ſche
    0.57
    Activations Density 0.006%

    No Known Activations