© 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. 9407
    Prev
    Next
    INDEX
    Explanations

    expressions indicating alternatives or substitutions

    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
    tagHelper
    -0.54
    */].
    -0.49
    Glej
    -0.48
    principalTable
    -0.43
     trick
    -0.43
     חיצוניים
    -0.43
    seamnă
    -0.42
    astify
    -0.42
     wireType
    -0.41
     KeyEvent
    -0.41
    POSITIVE LOGITS
     instead
    1.62
    instead
    1.34
     zamiast
    1.16
     вместо
    1.16
    Instead
    1.06
     anstatt
    1.05
     invece
    1.02
     Instead
    1.01
     rather
    0.92
     istället
    0.91
    Activations Density 0.101%

    No Known Activations