© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7576
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to statistical or quantitative analyses

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

    numerical fractions or ratios expressed with "of" (e.g., "out of", "X of Y").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     précédent
    -0.63
     sebelumnya
    -0.53
     précédente
    -0.52
    previous
    -0.52
     earlier
    -0.50
     previous
    -0.50
     предыду
    -0.49
     poprzed
    -0.47
     anteced
    -0.47
     précédentes
    -0.46
    POSITIVE LOGITS
     later
    0.78
    Later
    0.78
     Later
    0.74
     subsequently
    0.69
    later
    0.68
     subsequent
    0.67
     Subsequently
    0.65
     Subsequent
    0.62
     thereafter
    0.60
     arşivlendi
    0.59
    Activations Density 1.416%

    No Known Activations