© 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. 1-GEMMASCOPE-RES-16K
    11. 2822
    Prev
    Next
    INDEX
    Explanations

    the term "ob" and its variations, likely relating to observations or conditions involving "obstruction" or "obesity."

    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
     հղումներ
    -0.46
     AspNetCore
    -0.44
    hydrates
    -0.42
    ConstraintMaker
    -0.41
     springfox
    -0.41
    外部連結
    -0.41
     للاسماء
    -0.40
     lowercase
    -0.40
    anadas
    -0.40
    よいよ
    -0.40
    POSITIVE LOGITS
     ob
    3.36
    ob
    3.28
     Ob
    3.20
    Ob
    3.19
     OB
    2.53
    OB
    2.50
     Obs
    1.85
    obs
    1.72
     Obl
    1.70
    об
    1.56
    Activations Density 0.226%

    No Known Activations