© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64260
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols related to mathematical or programming contexts

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

    translated text or phrases

    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
     imagui
    -0.90
     témoig
    -0.86
     Normdatei
    -0.86
     beſti
    -0.82
     unſer
    -0.79
    ſſung
    -0.78
     pinulongan
    -0.77
    ⏔
    -0.77
     fashiola
    -0.77
    <unused68>
    -0.76
    POSITIVE LOGITS
     ​​
    0.36
     The
    0.33
     translated
    0.32
     estre
    0.32
    translation
    0.31
     resulta
    0.31
     Looks
    0.29
    🇧
    0.29
    信
    0.28
    translated
    0.28
    Activations Density 0.000%

    No Known Activations