© 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. 14309
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric values and associated metadata in a technical context

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

    scientific numbers and codes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    漫
    -0.30
     sli
    -0.30
    साय
    -0.28
     Viva
    -0.26
    름
    -0.26
    DOCTYPE
    -0.26
    ⎤
    -0.26
    天下
    -0.26
    ::*;
    -0.26
     hail
    -0.26
    POSITIVE LOGITS
    findpost
    0.81
    astify
    0.70
     يتيمه
    0.68
    WebVitals
    0.66
    twimg
    0.62
     noDo
    0.61
    expandindo
    0.60
     ErrIntOverflow
    0.60
    WriteTagHelper
    0.59
    aarrggbb
    0.58
    Activations Density 0.084%

    No Known Activations