© 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. 6827
    Prev
    Next
    INDEX
    Explanations

    words related to languages or cultural expressions

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

    non-English language text, particularly Malay and other non-Latin scripts.

    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
    LookAnd
    -0.64
    gående
    -0.49
     čierna
    -0.47
    impanan
    -0.47
     étrangère
    -0.46
     regalías
    -0.46
     télévis
    -0.45
    팎
    -0.45
     puissent
    -0.45
     devaient
    -0.43
    POSITIVE LOGITS
     AssemblyTitle
    0.56
    BASEPATH
    0.46
     utafitiHapana
    0.43
     mergeFrom
    0.43
    RenderAtEndOf
    0.41
    
    0.41
    adaptiveStyles
    0.40
     pinulongan
    0.40
     noDo
    0.39
    AddTagHelper
    0.39
    Activations Density 0.023%

    No Known Activations