© 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. 7969
    Prev
    Next
    INDEX
    Explanations

    several occurrences of the term "herein" and related terms indicating reference or incorporation of information within the text

    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
    somebody
    -0.86
    Somebody
    -0.84
     Somebody
    -0.81
    everybody
    -0.79
    Everybody
    -0.76
     somebody
    -0.75
     Everybody
    -0.74
    bigger
    -0.72
     maybe
    -0.72
     stuff
    -0.72
    POSITIVE LOGITS
    maktadır
    1.08
    mektedir
    1.03
     již
    0.99
     iż
    0.95
     endast
    0.93
     således
    0.93
     tersebut
    0.92
     jedoch
    0.91
    されており
    0.90
    にて
    0.90
    Activations Density 0.172%

    No Known Activations