© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21052
    Prev
    Next
    INDEX
    Explanations

    character names and significant terms in a fantasy or adventure context

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

    names like 'qiraj', 'Jark', 'ark'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    •Where Avali 2?

    No Comments

    Negative Logits
    ſelves
    -0.63
     Cæsar
    -0.56
    tats
    -0.55
    afy
    -0.54
    burton
    -0.54
     Majefty
    -0.53
     <<<<<<<<<<<<<<
    -0.53
     nob
    -0.52
    sizeCache
    -0.52
    ագրություններ
    -0.50
    POSITIVE LOGITS
     tatuagens
    0.47
     sacerdotes
    0.43
    vorschaubild
    0.40
     cenar
    0.39
    platten
    0.38
     Infórmanos
    0.38
     texturas
    0.38
     fatiga
    0.37
     creencias
    0.36
    vulas
    0.36
    Activations Density 0.115%

    No Known Activations