© 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. 3-GEMMASCOPE-RES-16K
    11. 9197
    Prev
    Next
    INDEX
    Explanations

    strong adjectives or descriptors indicating intensity or power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.63
     تضيفلها
    -0.49
     AppCompatTheme
    -0.47
    exitRule
    -0.47
    CPtr
    -0.47
    menuStrip
    -0.47
    DeleteBehavior
    -0.46
     defaultstate
    -0.45
    liflower
    -0.44
    EndInit
    -0.44
    POSITIVE LOGITS
     strong
    4.13
    strong
    3.80
    Strong
    3.73
     Strong
    3.69
     STRONG
    3.42
    STRONG
    3.22
     stronger
    2.88
     strongest
    2.80
     sterke
    2.73
     fuerte
    2.59
    Activations Density 0.100%

    No Known Activations