© 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. 7-GEMMASCOPE-RES-16K
    11. 15518
    Prev
    Next
    INDEX
    Explanations

    elements related to media literacy and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impacting
    -0.84
     leveraging
    -0.82
     impactful
    -0.81
     impacted
    -0.78
     broadly
    -0.77
    challenged
    -0.76
     foundational
    -0.76
     challenged
    -0.75
    endipity
    -0.75
    Folks
    -0.74
    POSITIVE LOGITS
    нибудь
    0.54
     kì
    0.47
    Außerdem
    0.46
    PointerException
    0.46
     Außerdem
    0.45
     giebt
    0.44
     riguardo
    0.42
    specialchars
    0.41
    ioutil
    0.41
    listdir
    0.41
    Activations Density 5.663%

    No Known Activations