© 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. 13681
    Prev
    Next
    INDEX
    Explanations

    programming and technical command language expressions

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

    Two- or three-letter fragments

    np_acts-logits-general · gemini-2.0-flash

    words ending in o

    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
     navideña
    -0.72
     alemana
    -0.72
     asiática
    -0.68
     chilena
    -0.66
     literaria
    -0.66
     navideño
    -0.64
     británica
    -0.64
     colgante
    -0.63
     interactiva
    -0.62
     inglesa
    -0.61
    POSITIVE LOGITS
    eo
    0.88
    o
    0.80
    oro
    0.79
    ono
    0.76
    ho
    0.76
    evo
    0.76
    olo
    0.75
    iro
    0.73
    onto
    0.73
    edo
    0.70
    Activations Density 0.776%

    No Known Activations