© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8895
    Prev
    Next
    INDEX
    Explanations

    words and phrases containing "um" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.47
    cientific
    -0.43
    RenderAtEndOf
    -0.43
    odacty
    -0.43
    contentLoaded
    -0.40
    
    -0.40
    TacToe
    -0.39
    rillation
    -0.39
     adap
    -0.39
     referrerpolicy
    -0.39
    POSITIVE LOGITS
     um
    0.91
    um
    0.83
     Um
    0.76
    uming
    0.75
    cum
    0.73
    rum
    0.72
    Um
    0.71
    ums
    0.71
     assumption
    0.71
     assumed
    0.69
    Activations Density 1.835%

    No Known Activations