Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 90605
    Prev
    Next
    INDEX
    Explanations

    references to "world," particularly in contexts related to technology or systems

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

    world

    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
    TabIndex
    -0.55
    ValueStyle
    -0.48
    getColumnIndex
    -0.47
    AnchorTagHelper
    -0.45
    ########.
    -0.43
    IntoConstraints
    -0.43
    BASEPATH
    -0.42
    sego
    -0.42
    equation
    -0.42
     Insee
    -0.41
    POSITIVE LOGITS
    world
    2.52
    World
    2.25
    WORLD
    2.14
     World
    1.95
     WORLD
    1.81
     world
    1.75
    orld
    1.57
    ワールド
    1.51
    worlds
    1.49
    世界
    1.43
    Activations Density 0.006%

    No Known Activations