© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15697
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or ambiguity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.56
    Slik
    -0.45
    WaitGroup
    -0.44
     GenerationType
    -0.44
    RunWith
    -0.43
    fjspx
    -0.43
    AxisAlignment
    -0.43
    исленность
    -0.43
    írus
    -0.42
    CloseOperation
    -0.42
    POSITIVE LOGITS
     blevet
    0.69
     blitt
    0.61
     Bestandteil
    0.50
     becoming
    0.50
     onderdeel
    0.49
     becomes
    0.49
     Erhaltung
    0.48
     Soyez
    0.47
     mijne
    0.47
     merupakan
    0.47
    Activations Density 0.575%

    No Known Activations