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

    Neuronpedia

    Jacobian LensNEW
    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. 5244
    Prev
    Next
    INDEX
    Explanations

    phrases expressing inability or frustration

    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
     savour
    -0.39
     quizá
    -0.38
     podjela
    -0.38
    깥
    -0.37
    zeits
    -0.37
     Peña
    -0.37
    　“
    -0.36
    

    -0.36
    issory
    -0.35
    釁
    -0.35
    POSITIVE LOGITS
    います
    1.45
    です
    1.38
    します
    1.36
    입니다
    1.28
    ました
    1.27
    いました
    1.26
    になります
    1.24
    ります
    1.20
     있습니다
    1.17
    しました
    1.16
    Activations Density 0.148%

    No Known Activations