© 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. 15-GEMMASCOPE-RES-16K
    11. 1319
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating emotional responses or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ClientSize
    -0.64
    frameCount
    -0.54
    Liar
    -0.53
    SYNOPSIS
    -0.51
    cticut
    -0.50
     bli
    -0.49
     seg
    -0.49
    槛
    -0.49
     Lie
    -0.48
    fart
    -0.48
    POSITIVE LOGITS
     Displays
    0.75
     displays
    0.75
     exhibiting
    0.74
    íncia
    0.74
    Personensuche
    0.73
    displays
    0.72
    noinspection
    0.72
     displaying
    0.71
    Displays
    0.70
    الدراسه
    0.70
    Activations Density 0.179%

    No Known Activations