© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104767
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical and physical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIPSETTING
    -0.45
    ContentLoaded
    -0.44
     aceptas
    -0.43
    getColumnIndex
    -0.43
     Backman
    -0.41
    ViewImports
    -0.41
    发表于
    -0.40
     EMPLOY
    -0.39
     octobre
    -0.39
     فريبيس
    -0.39
    POSITIVE LOGITS
    NameInMap
    0.69
    mathbf
    0.60
    migrationBuilder
    0.55
     dezelve
    0.55
    期刊论文
    0.53
    mathfrak
    0.52
     grammi
    0.51
     تضيفلها
    0.50
    mathcal
    0.49
    mathit
    0.49
    Activations Density 0.011%

    No Known Activations