© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 584
    Prev
    Next
    INDEX
    Explanations

    expressions of boredom and dissatisfaction with experiences or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Negative sentiment, like "boring" or "tired"

    np_acts-logits-general · gemini-2.0-flash

    boring, tired, unoriginal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.54
    CrossRef
    -0.49
    ⤹
    -0.47
     Italijanski
    -0.46
     GenerationType
    -0.45
    windowFixed
    -0.43
    Personendaten
    -0.43
     laiko
    -0.43
     kasarigan
    -0.43
    licone
    -0.41
    POSITIVE LOGITS
     boring
    0.67
    Boring
    0.63
     Boring
    0.60
     uninteresting
    0.57
     bland
    0.56
     monotonous
    0.54
     dull
    0.52
    boring
    0.51
     mundane
    0.50
     monotony
    0.49
    Activations Density 0.358%

    No Known Activations