© 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. 14-GEMMASCOPE-RES-16K
    11. 8359
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to the concept of "super" typically indicating something of high quality or enhanced properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iArr
    -0.45
    lineno
    -0.44
    apse
    -0.43
    NCIA
    -0.43
    tizia
    -0.43
     carteira
    -0.43
    Voci
    -0.42
    <bos>
    -0.42
    sieh
    -0.41
     Waltz
    -0.41
    POSITIVE LOGITS
     super
    1.60
     Super
    1.47
     SUPER
    1.45
    Super
    1.41
    super
    1.33
    SUPER
    1.27
     супер
    1.11
     súper
    1.08
     fuper
    1.04
    超级
    1.02
    Activations Density 0.145%

    No Known Activations