© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103796
    Prev
    Next
    INDEX
    Explanations

    terms related to fandom or popular culture references

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

    First tokens of attribution lines, bylines, or reference identifiers in different types of published content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ロウィン
    -0.99
     imagui
    -0.95
     témoig
    -0.95
    niſſe
    -0.95
    iſchen
    -0.90
    ﹧
    -0.90
    linawan
    -0.89
    хьтан
    -0.88
    ⤹
    -0.87
    ſchaft
    -0.87
    POSITIVE LOGITS
    -
    0.35
     
    0.29
    2
    0.29
    _
    0.29
    ’
    0.29
    的
    0.29
     was
    0.29
    1
    0.28
    ta
    0.28
    <strong>
    0.28
    Activations Density 0.040%

    No Known Activations