© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 10159
    Prev
    Next
    INDEX
    Explanations

    key terms related to the number and classification of features or characteristics

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

    listing limitations or issues

    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
    unteers
    -0.51
    chartInstance
    -0.49
    AnchorTagHelper
    -0.48
    elemField
    -0.47
     المعيارى
    -0.47
    UrlResolution
    -0.47
    فایل‌لار
    -0.45
    SpringRunner
    -0.45
    __(/*!
    -0.44
     Entities
    -0.44
    POSITIVE LOGITS
     important
    0.59
     specific
    0.56
     remarkable
    0.50
     major
    0.49
    specific
    0.49
     unique
    0.49
     significant
    0.48
    important
    0.46
     fundamental
    0.46
     listed
    0.46
    Activations Density 0.105%

    No Known Activations