© 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. 55948
    Prev
    Next
    INDEX
    Explanations

    phrases related to satisfying or failing to satisfy assumptions in a mathematical context

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

    satisfy the assumption

    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
     espoir
    -0.29
    Cidade
    -0.28
     koko
    -0.28
    Equals
    -0.27
     corta
    -0.26
     bet
    -0.26
    länd
    -0.26
    mappedBy
    -0.26
    ("")]
    
    -0.26
     presidencia
    -0.26
    POSITIVE LOGITS
    MigrationBuilder
    0.82
     Italijanski
    0.72
    jsxFileName
    0.69
     ModelExpression
    0.67
    sizeCache
    0.67
    Geplaatst
    0.66
     queſta
    0.64
     Fitting
    0.62
     تضيفلها
    0.61
    PyExc
    0.60
    Activations Density 0.505%

    No Known Activations