© 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. 39151
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "core" or essential elements in various contexts

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

    core followed by a 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
    ambiguation
    -0.54
     Wilkinson
    -0.49
    noinspection
    -0.47
     ListView
    -0.47
    vertising
    -0.47
    measurement
    -0.46
     Measurement
    -0.46
    vibration
    -0.45
    ctuation
    -0.45
    addington
    -0.45
    POSITIVE LOGITS
    Core
    1.25
     Core
    1.23
     core
    1.21
     CORE
    1.16
    core
    1.16
    CORE
    1.04
    核心
    0.85
     cores
    0.81
    コア
    0.77
     Cores
    0.77
    Activations Density 0.013%

    No Known Activations