© 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. 58639
    Prev
    Next
    INDEX
    Explanations

    terms related to acceleration and deceleration in a technical context

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

    acceleration and deceleration

    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
     оригіналу
    -0.69
     ostavi
    -0.69
     <<<<<<<<<<<<<<
    -0.66
    PYX
    -0.66
    AsUp
    -0.66
     AssemblyTitle
    -0.64
     pinulongan
    -0.63
    出版年
    -0.62
    localctx
    -0.59
    nloa
    -0.59
    POSITIVE LOGITS
     acceleration
    0.73
    Acceleration
    0.66
    acceleration
    0.65
     Acceleration
    0.62
     deceleration
    0.44
     aceler
    0.43
     acceler
    0.43
    accel
    0.38
     Acceler
    0.37
     accelerate
    0.37
    Activations Density 0.011%

    No Known Activations