© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10661
    Prev
    Next
    INDEX
    Explanations

    nouns and articles, particularly in the context of Spanish language usage

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

    "necesito" after "lo"

    np_acts-logits-general · gemini-2.0-flash

    lo necesito

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.74
     Czechoslovakia
    -0.72
     Cister
    -0.70
     '\\;'
    -0.70
     ་་
    -0.66
     Cæsar
    -0.65
     wikipagina
    -0.65
     Esau
    -0.65
     ſche
    -0.65
     Shakspeare
    -0.65
    POSITIVE LOGITS
     same
    1.31
     latter
    1.11
     most
    1.05
     main
    0.95
     following
    0.94
     entire
    0.94
     fact
    0.94
     respective
    0.93
     whole
    0.92
     latest
    0.91
    Activations Density 0.019%

    No Known Activations