© 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. 111650
    Prev
    Next
    INDEX
    Explanations

    phrases related to ownership and affirmation of responsibility

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

    diatoms

    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
    webElementXpaths
    -0.59
     étoit
    -0.49
     Administrativna
    -0.47
     مؤرشف
    -0.45
    úgó
    -0.44
     francès
    -0.43
    曖昧さ回避
    -0.42
    Personensuche
    -0.42
     '\\;'
    -0.41
     <>",
    -0.41
    POSITIVE LOGITS
    ⟬
    0.46
    InstanceState
    0.40
    StandardCharsets
    0.37
     Probes
    0.37
     Elbow
    0.37
     CEN
    0.36
     getColumn
    0.36
    tdb
    0.36
    `,
    
    0.35
    SpringBootTest
    0.35
    Activations Density 0.001%

    No Known Activations