© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5801
    Prev
    Next
    INDEX
    Explanations

    specific measurements and statistics related to physical characteristics or medical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.56
    URLException
    -0.55
    RTLR
    -0.52
    httphttps
    -0.51
    PerformLayout
    -0.50
    ollectionView
    -0.49
     MenuView
    -0.48
     utafitiHapana
    -0.48
    ioutil
    -0.47
     مشين
    -0.47
    POSITIVE LOGITS
     bertahan
    0.42
     desnuda
    0.41
     pitä
    0.41
     plumas
    0.41
     capucha
    0.40
     burbujas
    0.38
     związane
    0.38
     romántica
    0.36
     parecido
    0.36
    řevě
    0.36
    Activations Density 1.970%

    No Known Activations