© 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. 27-GEMMASCOPE-RES-16K
    6. 10460
    Prev
    Next
    INDEX
    Explanations

    instances of the word "super" and its variations, indicating a focus on superlative qualities or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorin
    -0.38
    <h2>
    -0.38
     ciutat
    -0.37
     novios
    -0.36
    <h5>
    -0.35
     zwró
    -0.35
     dudas
    -0.35
    Path
    -0.34
     Fotografía
    -0.34
     Evaluación
    -0.34
    POSITIVE LOGITS
     SUPER
    1.16
     super
    1.16
     Super
    1.14
    Super
    1.07
    SUPER
    1.06
    super
    1.01
     supers
    0.93
     Supers
    0.93
     fuper
    0.90
    Supers
    0.85
    Activations Density 0.202%

    No Known Activations