© 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. 27-GEMMASCOPE-RES-16K
    6. 8742
    Prev
    Next
    INDEX
    Explanations

    words associated with various technical and scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.40
    smöglichkeiten
    -0.40
    ADORES
    -0.38
    /******/
    -0.37
    ingtones
    -0.36
     versions
    -0.35
    ⎨
    -0.35
     batteries
    -0.35
     öffnungszeiten
    -0.34
     calitate
    -0.34
    POSITIVE LOGITS
     يتيمه
    0.76
     quelqu
    0.56
    someone
    0.56
     iemand
    0.55
     someplace
    0.53
     someone
    0.53
     alguien
    0.52
     snippetHide
    0.52
    Datuak
    0.50
    Demografie
    0.50
    Activations Density 0.988%

    No Known Activations