© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 5102
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to feelings of comfort and positivity

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

    Follows adjectives describing feelings

    np_acts-logits-general · gemini-2.0-flash

    pleasantly surprised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élastique
    -0.56
     pinulongan
    -0.55
     quelcon
    -0.51
     valiant
    -0.50
     disambiguazione
    -0.49
     myſelf
    -0.49
     préfé
    -0.48
     preventivo
    -0.48
     wahre
    -0.47
    RTEX
    -0.47
    POSITIVE LOGITS
     imperfection
    0.63
     imperfections
    0.61
     imperfect
    0.58
     crazy
    0.57
     madness
    0.54
     chaos
    0.54
     weird
    0.53
     craz
    0.52
     stupidity
    0.52
     misery
    0.52
    Activations Density 0.461%

    No Known Activations