© 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. 20-GEMMASCOPE-RES-131K
    11. 53031
    Prev
    Next
    INDEX
    Explanations

    hyphenated compound words or terms related to scientific or technical concepts

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

    hyphenated adjective followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    WillAppear
    -0.78
    DIPSETTING
    -0.67
    WaitGroup
    -0.62
    UnitTesting
    -0.62
    原始内容存档于
    -0.62
    GraphicsUnit
    -0.61
     Roskov
    -0.60
     <<<<<<<<<<<<<<
    -0.59
     تضيفلها
    -0.58
     propOrder
    -0.58
    POSITIVE LOGITS
     Crusoe
    0.46
     fossil
    0.45
     Cycl
    0.44
     dron
    0.43
     hybrid
    0.42
     Chanti
    0.42
     Riti
    0.42
     physical
    0.41
     celib
    0.41
     Bree
    0.41
    Activations Density 0.135%

    No Known Activations