© 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. 2-GEMMASCOPE-RES-16K
    11. 5126
    Prev
    Next
    INDEX
    Explanations

    terms related to the creation and publication of documents or works

    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
     agreed
    -0.40
     indicated
    -0.40
     approved
    -0.38
     met
    -0.37
     followed
    -0.37
     included
    -0.37
     linked
    -0.37
     provided
    -0.36
     moved
    -0.36
     reached
    -0.36
    POSITIVE LOGITS
    Created
    1.34
     Created
    1.33
    Played
    1.17
    Made
    1.16
     Made
    1.15
    Developed
    1.13
    Published
    1.13
    Posted
    1.11
     Designed
    1.11
    Written
    1.10
    Activations Density 0.323%

    No Known Activations