© 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. 9-GEMMASCOPE-RES-131K
    6. 28440
    Prev
    Next
    INDEX
    Explanations

    themes related to life stages and societal roles

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

    verbs followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.75
    Билгалдахарш
    -0.50
    ؤلاء
    -0.50
    __":
    -0.48
    Cyfarwyddwr
    -0.47
    ExecuteReader
    -0.47
    Personendaten
    -0.46
     pageContext
    -0.44
    httphttps
    -0.44
     للاسماء
    -0.44
    POSITIVE LOGITS
     doccia
    0.43
    MessageTagHelper
    0.43
     cuillère
    0.38
     estadísticas
    0.34
     hjär
    0.33
     psicológico
    0.32
     humaines
    0.31
    цездатний
    0.31
    SEGUIR
    0.31
     corrupción
    0.31
    Activations Density 0.226%

    No Known Activations