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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4263
    Prev
    Next
    INDEX
    Explanations

    phrases related to upward or outward movement

    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
    verifyException
    -0.90
     ModelExpression
    -0.79
    IsContent
    -0.76
     estekak
    -0.76
    Искәрмәләр
    -0.74
     مشين
    -0.73
    mobileqq
    -0.73
    InjectAttribute
    -0.72
    PreferredItem
    -0.72
     חיצוניים
    -0.71
    POSITIVE LOGITS
     up
    0.65
     away
    0.48
     out
    0.46
     off
    0.46
    2
    0.44
    ↵
    0.43
    les
    0.38
    3
    0.37
    &
    0.37
    1
    0.36
    Activations Density 0.226%

    No Known Activations