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

    Neuronpedia

    Jacobian LensNEW
    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. 1-GEMMASCOPE-RES-16K
    11. 7402
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to databases and data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spitze
    -0.57
     Decke
    -0.49
    er
    -0.49
    -
    -0.48
     totalidad
    -0.46
    ing
    -0.46
     encarga
    -0.44
     olmayan
    -0.43
     Tiefe
    -0.42
     venons
    -0.42
    POSITIVE LOGITS
     df
    1.27
     fb
    1.23
     pt
    1.20
     bp
    1.19
     lp
    1.18
     hd
    1.17
     dp
    1.16
     dt
    1.16
     bb
    1.16
     cp
    1.15
    Activations Density 0.388%

    No Known Activations