© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12792
    Prev
    Next
    INDEX
    Explanations

    terms related to military units or organizational categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kebijakan
    -0.56
    featureID
    -0.52
    تقاوى
    -0.52
    푢
    -0.47
    Personendaten
    -0.47
    positiva
    -0.46
    WillAppear
    -0.45
     unſer
    -0.45
    ReusableCell
    -0.45
     Meksiku
    -0.44
    POSITIVE LOGITS
     Um
    1.09
     Unit
    1.06
     Un
    1.06
    Um
    1.05
     Uh
    1.02
     Ur
    0.99
    Us
    0.98
    Un
    0.98
     У
    0.98
     Us
    0.97
    Activations Density 0.512%

    No Known Activations