© 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. 1121
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the concept of "also" or "too" in various contexts

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

    also auch wenn

    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
     also
    -1.11
    also
    -0.86
     також
    -0.85
     также
    -0.84
     também
    -0.84
     también
    -0.82
     ALSO
    -0.80
     Also
    -0.80
     cũng
    -0.78
     też
    -0.77
    POSITIVE LOGITS
     Infórmanos
    0.58
     تضيفلها
    0.57
     CanadaChoose
    0.56
    ंदीखरीदारी
    0.56
     Мексичка
    0.51
     EClass
    0.51
    Parcelize
    0.50
     wenn
    0.50
     كومونز
    0.49
     aquí
    0.49
    Activations Density 0.019%

    No Known Activations