© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 20975
    Prev
    Next
    INDEX
    Explanations

    words or prefixes related to various forms of "y" or "i" endings

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

    names ending in y

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    bleau
    -0.54
    cln
    -0.50
    hspace
    -0.50
    multicolumn
    -0.49
     vandens
    -0.48
     kommet
    -0.48
     tilbud
    -0.48
     onCancelled
    -0.47
    alış
    -0.47
     begren
    -0.47
    POSITIVE LOGITS
    y
    1.05
    ry
    0.93
    ey
    0.90
    dy
    0.89
    ty
    0.88
    yyyy
    0.88
    ky
    0.84
    ety
    0.83
    gy
    0.82
    vy
    0.81
    Activations Density 0.197%

    No Known Activations