© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1253
    Prev
    Next
    INDEX
    Explanations

    mechanical components and their interactions in machinery

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

    Mechanical components or motion

    np_acts-logits-general · gemini-2.0-flash

    mechanical components and motion

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ainfi
    -0.59
    ⟬
    -0.59
     CreateTagHelper
    -0.57
    RegressionTest
    -0.54
     Houſe
    -0.54
     plufieurs
    -0.54
    efois
    -0.52
     vettoriale
    -0.51
     queſta
    -0.50
     ſche
    -0.50
    POSITIVE LOGITS
     mechanical
    0.64
     Mechanical
    0.54
    Mechanical
    0.54
     MECHANICAL
    0.50
     mechan
    0.47
    mechanical
    0.47
     mec
    0.46
     mechanism
    0.46
     lub
    0.45
     motion
    0.45
    Activations Density 0.752%

    No Known Activations