© 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. 12-GEMMASCOPE-RES-16K
    11. 10963
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strong" and its variations, indicating a focus on strength or intensity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.67
    JsonPropertyName
    -0.57
    contentLoaded
    -0.55
    exitRule
    -0.54
    CPtr
    -0.52
     useAppContext
    -0.50
    StructEnd
    -0.49
     iconTwitter
    -0.49
    Rhestr
    -0.48
     [](
    -0.47
    POSITIVE LOGITS
    strong
    1.74
     strong
    1.73
    Strong
    1.65
     Strong
    1.64
     STRONG
    1.63
    STRONG
    1.59
     stronger
    1.46
     strongest
    1.41
     strength
    1.38
     Stronger
    1.38
    Activations Density 0.122%

    No Known Activations