© 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. 5113
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "UM" and variations related to it

    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
    évaluateur
    -0.46
    yntaxException
    -0.40
     MenuView
    -0.39
     maxn
    -0.35
     sucre
    -0.35
    skraft
    -0.35
     wireType
    -0.34
     utafitiHapana
    -0.34
    Directive
    -0.34
    ību
    -0.33
    POSITIVE LOGITS
    UM
    2.28
    um
    2.23
    ums
    2.17
     um
    2.08
     UM
    2.02
     Um
    1.99
    Um
    1.91
    umm
    1.82
    umi
    1.73
    umb
    1.70
    Activations Density 0.425%

    No Known Activations