© 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
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9397
    Prev
    Next
    INDEX
    Explanations

    elements related to text formatting and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.45
    seguida
    -0.43
     îna
    -0.39
     helft
    -0.38
     waarop
    -0.38
     pendekatan
    -0.36
     męska
    -0.36
     înc
    -0.36
     tacón
    -0.35
     acaso
    -0.34
    POSITIVE LOGITS
    Jegyzetek
    0.69
     Hungarian
    0.65
    TagHelper
    0.65
     budapest
    0.61
    省市镇
    0.61
     ſind
    0.60
     Houſe
    0.59
    thâu
    0.58
     itſelf
    0.58
     Hungary
    0.57
    Activations Density 0.604%

    No Known Activations