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

    Neuronpedia

    Jacobian LensNEW
    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. 6901
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to beliefs and existential reflections

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

    superlative or emphatic statements using "so" with intensifying adjectives or adverbs.

    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
     يتيمه
    -0.80
    sidemargin
    -0.75
     Chwiliwch
    -0.74
     nahilalakip
    -0.71
    findpost
    -0.69
     للاسماء
    -0.69
     defaultstate
    -0.68
    PYX
    -0.68
     للمعارف
    -0.65
    liceerd
    -0.65
    POSITIVE LOGITS
     so
    2.67
     begitu
    1.78
     så
    1.76
     tantas
    1.74
     tantos
    1.69
    這麼
    1.64
    如此
    1.63
    这么多
    1.61
     tão
    1.59
    那麼
    1.59
    Activations Density 0.900%

    No Known Activations