© 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. 13664
    Prev
    Next
    INDEX
    Explanations

    the phrase "no longer" indicating the cessation or termination of a state or condition

    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
    ďaka
    -0.42
     labores
    -0.42
     vandens
    -0.41
     gyóg
    -0.40
    expandindo
    -0.39
     MyBatis
    -0.37
    interopRequire
    -0.36
     naudo
    -0.36
     mög
    -0.36
    ayaquil
    -0.35
    POSITIVE LOGITS
     internet
    0.81
    SourceChecksum
    0.61
    internet
    0.60
     dAtA
    0.54
    :✨
    0.51
    Initializable
    0.50
     charges
    0.47
    UnifiedTopology
    0.47
     yyr
    0.46
    StoreMessageInfo
    0.46
    Activations Density 0.112%

    No Known Activations